# mcp.film — full directory > A curated, agent-readable directory of the best Model Context Protocol (MCP) servers for generative AI filmmaking — video generation, voice, music, editing, upscaling, distribution, and the full production stack. Generated 2026-06-11T07:00:35.155Z. 56 servers. Canonical JSON: https://mcp.film/api/registry.json --- # Adobe Premiere Pro MCP > Drive Premiere Pro timelines, effects, and exports from your agent via a CEP bridge. - **Category:** Editing & Post - **Vendor:** Community (hetpatel-11) (community) - **Pricing:** free - **Verified:** 2026-06-11 ## What it does 97-tool MCP server that controls Premiere Pro through a CEP extension bridge: import media, edit sequences, apply effects and transitions, and export. Lets an agent do real NLE assembly inside the editor filmmakers already use. ## Connect - Follow the vendor's instructions: see links below **Auth:** local-app — Requires Premiere Pro 2020+ running with the bundled 'MCP Bridge' CEP extension ## Capabilities `nle-control` · `timeline-editing` · `effects` · `render` · `media-management` ## Sample tools `import_media` · `apply_effect` · `add_transition` · `get_sequences` · `get_active_sequence` · `export_sequence` ## Field notes 272 stars, active through Jun 2026, MIT — the most-starred Premiere MCP (Adobe has no official one). Install is git clone + npm setup; macOS is the primary platform. Newer alternative: leancoderkavy/premiere-pro-mcp (269 tools). ## Links - Repo: https://github.com/hetpatel-11/Adobe_Premiere_Pro_MCP --- Structured data: https://mcp.film/api/mcps/premiere-pro.json · Directory: https://mcp.film --- # After Effects MCP > Automate After Effects comps, layers, and keyframes through MCP + ExtendScript. - **Category:** Editing & Post - **Vendor:** Community (Dakkshin) (community) - **Pricing:** free - **Verified:** 2026-06-11 ## What it does MCP server that remote-controls Adobe After Effects: create compositions, text/shape/solid layers, cameras, masks, keyframes, and expressions. Useful for agent-driven motion graphics, titles, and VFX passes on generated footage. ## Connect - Follow the vendor's instructions: see links below **Auth:** local-app — Requires After Effects 2022+ with the 'mcp-bridge-auto' panel open ## Capabilities `motion-graphics` · `compositing` · `animation` · `nle-control` ## Sample tools `create-composition` · `setLayerKeyframe` · `setLayerProperties` · `createCamera` · `setLayerMask` ## Field notes 416 stars, MIT, active Jun 2026 — the most popular AE MCP. Install: git clone, npm install/build, install-bridge. For template-based AE rendering in the cloud, see plainly-videos/mcp-server (official Plainly API MCP). ## Links - Repo: https://github.com/Dakkshin/after-effects-mcp --- Structured data: https://mcp.film/api/mcps/after-effects.json · Directory: https://mcp.film --- # Airtable MCP Server > Official hosted Airtable MCP: query, create, and update production-tracking bases. - **Category:** Production Ops - **Vendor:** Airtable (official) - **Pricing:** freemium - **Verified:** 2026-06-11 ## What it does Airtable's official remote MCP server lets agents search bases, read schemas, filter/sort records, create and update rows, and read interface pages — ideal for shot trackers, casting sheets, asset libraries, and budgets. OAuth via Dynamic Client Registration (or a personal access token), and it enforces each user's existing Airtable permissions. ## Connect - Remote endpoint: `https://mcp.airtable.com/mcp` - Claude Code: `claude mcp add --transport http airtable https://mcp.airtable.com/mcp` **Auth:** oauth — OAuth browser flow (primary); PATs also supported at https://airtable.com/create/tokens ## Capabilities `base-search` · `schema-inspection` · `record-crud` · `record-search` · `comments` · `table-creation` · `interface-pages` ## Sample tools `search_bases` · `list_tables_for_base` · `get_table_schema` · `list_records_for_table` · `search_records` · `create_records_for_table` · `update_records_for_table` · `create_table` ## Field notes Tool names verified directly against the live official server. Permissions-aware (read-only access stays read-only via MCP). Community stdio alternative: domdomegg/airtable-mcp-server (447 stars, npx airtable-mcp-server with a PAT). ## Links - Site: https://www.airtable.com - Docs: https://support.airtable.com/docs/using-the-airtable-mcp-server --- Structured data: https://mcp.film/api/mcps/airtable.json · Directory: https://mcp.film --- # AudioGen MCP > Free, local sound-effect generation with Meta's AudioGen — no API key needed. - **Category:** Sound Design & SFX - **Vendor:** Community (peerjakobsen) (community) - **Pricing:** free - **Verified:** 2026-06-11 ## What it does Community MCP server that runs Meta's AudioGen (AudioCraft) locally to generate sound effects from text descriptions, with async job tracking. Attractive for filmmakers who want unlimited, offline, no-cost SFX drafts without sending prompts to a cloud API; the model (~2GB) downloads from Hugging Face on first run. ## Connect - Follow the vendor's instructions: see links below **Auth:** none — No key needed; model auto-downloads from Hugging Face Hub ## Capabilities `sfx` · `local-inference` · `job-queue` ## Sample tools `generate_sound_effect` · `check_generation_status` · `list_generated_sounds` ## Field notes Very early stage (v0.1.0, Jan 2026), Apple Silicon only, manual Python 3.11 venv setup required. For higher-quality cloud SFX, prefer ElevenLabs text_to_sound_effects or CassetteAI SFX via the fal MCP. ## Links - Repo: https://github.com/peerjakobsen/audiogen-mcp --- Structured data: https://mcp.film/api/mcps/audiogen.json · Directory: https://mcp.film --- # Auphonic (via Zapier MCP) > Auphonic's AI audio post (loudness, leveling, denoise) reachable through Zapier MCP. - **Category:** Sound Design & SFX - **Vendor:** Auphonic / Zapier (community) - **Pricing:** freemium - **Verified:** 2026-06-11 ## What it does Auphonic is the de facto automated audio post-production service — loudness normalization to broadcast specs, speech leveling, denoising, de-essing, and filler-word cutting. It has no first-party MCP server; Zapier's hosted MCP exposes Auphonic actions to agents, making it the verified route for agent-driven dialogue cleanup and final-mix loudness compliance. ## Connect - Follow the vendor's instructions: https://auphonic.com/help/ **Auth:** oauth — Zapier account + Auphonic connection; per-user MCP endpoint generated in the Zapier MCP dashboard ## Capabilities `audio-cleanup` · `loudness-normalization` · `denoising` · `leveling` · `mastering` ## Field notes A generic Zapier MCP wrapper, not a dedicated audio MCP — tool granularity depends on Zapier's Auphonic actions, and the endpoint URL is per-user. Auphonic offers 2 free processing hours/month. Listed because audio cleanup/mastering otherwise has no notable dedicated MCP as of June 2026 (ElevenLabs isolate_audio is the nearest alternative for dialogue denoise). ## Links - Site: https://zapier.com/mcp/auphonic - Docs: https://auphonic.com/help/ --- Structured data: https://mcp.film/api/mcps/auphonic-zapier.json · Directory: https://mcp.film --- # Blender MCP > The canonical Blender MCP — model, texture, and assemble 3D scenes by prompt. - **Category:** 3D, Worlds & VFX - **Vendor:** Community (ahujasid) (community) - **Pricing:** free - **Verified:** 2026-06-11 ## What it does Two-way bridge between AI agents and Blender: inspect scenes, create/modify objects and materials, and execute arbitrary Python in Blender. With Poly Haven, Sketchfab, and Hyper3D Rodin integrations, an agent can pull assets and build previz sets or full shots. ## Connect - Claude Code: `claude mcp add blender -- uvx blender-mcp` - Local: `uvx blender-mcp` **Auth:** local-app — Requires Blender 3.0+ running with the bundled addon installed and its socket server started ## Capabilities `3d-scene-control` · `asset-import` · `python-scripting` · `render` · `previz` ## Sample tools `execute_blender_code` ## Field notes 22.6k stars — by far the most popular DCC MCP; v1.5.5, pushed Jun 2026, MIT. execute_blender_code runs arbitrary Python — save your work first. Telemetry on by default (disable via DISABLE_TELEMETRY). Asset integrations: Poly Haven (free), Sketchfab, Hyper3D Rodin. ## Links - Repo: https://github.com/ahujasid/blender-mcp --- Structured data: https://mcp.film/api/mcps/blender.json · Directory: https://mcp.film --- # CapCut MCP > Build CapCut/Jianying draft projects programmatically from an AI agent. - **Category:** Editing & Post - **Vendor:** Community (fancyboi999) (community) - **Pricing:** free - **Verified:** 2026-06-11 ## What it does Python server exposing CapCut draft creation over HTTP/MCP: add video, audio, images, text, subtitles, effects, and stickers, then save as a draft folder that opens in CapCut for finishing. Lets agents pre-assemble social edits that humans polish in CapCut. ## Connect - Follow the vendor's instructions: see links below **Auth:** none ## Capabilities `nle-control` · `draft-generation` · `captioning` · `effects` ## Sample tools `create_draft` · `add_video` · `add_audio` · `add_text` · `add_subtitle` · `add_effect` · `save_draft` ## Field notes 84 stars, active Jun 2026; no official ByteDance MCP exists. Workflow caveat: generated draft folders must be manually copied into CapCut's drafts directory; needs ffmpeg + Python 3.8; docs partly Chinese; no license file. ## Links - Repo: https://github.com/fancyboi999/capcut-mcp --- Structured data: https://mcp.film/api/mcps/capcut.json · Directory: https://mcp.film --- # Cartesia MCP > Official Cartesia (Sonic) server: low-latency TTS, voice cloning, infill, localization. - **Category:** Voice & Dialogue - **Vendor:** Cartesia (official) - **Pricing:** freemium - **Verified:** 2026-06-11 ## What it does Cartesia's official MCP server exposes its Sonic voice stack: TTS, speech-to-text, voice cloning, voice changing, and notably audio infill (generate speech between two existing clips) and voice localization into other languages. Strong for ADR-style dialogue patching and localizing a character's voice across language versions. ## Connect - Claude Code: `claude mcp add cartesia -e CARTESIA_API_KEY=YOUR_KEY -- uvx cartesia-mcp` - Local: `uvx cartesia-mcp` **Auth:** api_key (env `CARTESIA_API_KEY`) — https://play.cartesia.ai/keys ## Capabilities `tts` · `stt` · `voice-cloning` · `voice-changing` · `infill` · `localization` ## Sample tools `text_to_speech` · `speech_to_text` · `list_voices` · `clone_voice` · `voice_change` · `localize_voice` · `infill` · `get_credit_usage` ## Field notes Officially supported, on PyPI as cartesia-mcp; ~16 tools. Optional CARTESIA_ADMIN_API_KEY enables account-management tools; OUTPUT_DIRECTORY controls where audio is saved. ## Links - Site: https://www.cartesia.ai - Docs: https://docs.cartesia.ai/tools/ai/mcp - Repo: https://github.com/cartesia-ai/cartesia-mcp --- Structured data: https://mcp.film/api/mcps/cartesia.json · Directory: https://mcp.film --- # ComfyUI MCP > Drive a local ComfyUI: 40+ tools for image, video, audio and 3D workflows. - **Category:** Model Hubs - **Vendor:** Community (shawnrushefsky) (community) - **Pricing:** free - **Verified:** 2026-06-11 ## What it does Connects agents to a local or remote ComfyUI instance with 40+ tools for running, validating, composing and managing node workflows, plus 70+ bundled example workflows (FLUX, SDXL, SD3.5, ControlNet, LTX-Video, Mochi, AnimateDiff, Stable Audio). The free/local route for filmmakers who own GPUs and want full pipeline control, including open video models. ## Connect - Claude Code: `claude mcp add comfyui -- docker run -i --rm --pull always -e COMFYUI_URL=http://host.docker.internal:8000 ghcr.io/shawnrushefsky/comfyui-mcp:latest` - Local: `docker run -i --rm --pull always -e COMFYUI_URL=http://host.docker.internal:8000 ghcr.io/shawnrushefsky/comfyui-mcp:latest` **Auth:** none (env `COMFYUI_URL`) — Points at your own ComfyUI instance (default port 8188) — no cloud account needed ## Capabilities `text-to-image` · `image-to-image` · `text-to-video` · `audio-generation` · `3d-generation` · `workflow-execution` · `local-inference` ## Sample tools `run_workflow` · `validate_workflow` · `search_templates` · `get_example_workflow` · `build_node` · `list_models` · `get_queue` · `recommend_workflow` ## Field notes MIT; the most comprehensive ComfyUI MCP. Notable alternatives: artokun/comfyui-mcp (Claude Code plugin with slash commands/skills) and joenorton/comfyui-mcp-server (lightweight Python). Requires you to run ComfyUI yourself. ## Links - Site: https://www.comfy.org - Repo: https://github.com/shawnrushefsky/comfyui-mcp --- Structured data: https://mcp.film/api/mcps/comfyui.json · Directory: https://mcp.film --- # ComfyUI MCP (Claude Code plugin) > Run and debug ComfyUI workflows from Claude Code — generate, validate, manage VRAM. - **Category:** 3D, Worlds & VFX - **Vendor:** Community (artokun) (community) - **Pricing:** free - **Verified:** 2026-06-11 ## What it does TypeScript MCP server + Claude Code plugin for ComfyUI: execute and validate workflows, visualize node graphs, search and download models, and manage GPU memory. The glue for agentic VFX pipelines built on ComfyUI (img2img cleanup, style passes, video nodes). ## Connect - Claude Code: `claude plugin install comfyui-mcp` - Local: `npx -y comfyui-mcp` **Auth:** local-app — Requires ComfyUI running (auto-detects ports 8188/8000, or --comfyui-url for remote) ## Capabilities `workflow-execution` · `image-generation` · `vfx-pipeline` · `model-management` ## Sample tools `generate_image` · `enqueue_workflow` · `visualize_workflow` · `search_models` · `validate_workflow` · `clear_vram` ## Field notes 142 stars, v0.9.4 (Jun 2026), MIT, very active; needs Node >=22. Most-starred Python alternative: joenorton/comfyui-mcp-server (350 stars); comfy-pilot (207 stars) focuses on workflow editing. ## Links - Repo: https://github.com/artokun/comfyui-mcp --- Structured data: https://mcp.film/api/mcps/comfyui-artokun.json · Directory: https://mcp.film --- # D-ID MCP Server > D-ID's hosted MCP connecting agents to the D-ID API and docs for avatar video. - **Category:** Avatars & Performance - **Vendor:** D-ID (official) - **Pricing:** freemium - **Verified:** 2026-06-11 ## What it does D-ID hosts an official remote MCP server on its developer docs that lets MCP clients interact with the D-ID API and its documentation for talking-avatar and Agents workflows. D-ID also publishes llms.txt for agent consumption. ## Connect - Remote endpoint: `https://docs.d-id.com/mcp` - Claude Code: `claude mcp add --transport http d-id https://docs.d-id.com/mcp` **Auth:** api_key — https://docs.d-id.com/docs/api-keys (D-ID Studio; credits required for API calls) ## Capabilities `avatar-video` · `talking-head` · `docs-search` · `agents-api` ## Field notes Docs-platform-hosted (ReadMe-powered) remote MCP; exact tool list not published openly. Landscape note: Synthesia has no official MCP as of June 2026 (only marginal community wrappers and generic Zapier/viaSocket gateways). ## Links - Site: https://www.d-id.com - Docs: https://docs.d-id.com/docs/mcp --- Structured data: https://mcp.film/api/mcps/d-id.json · Directory: https://mcp.film --- # DaVinci Resolve MCP > Full AI control of DaVinci Resolve Studio — edit, grade, Fusion, and render via scripting. - **Category:** Editing & Post - **Vendor:** Community (samuelgursky) (community) - **Pricing:** free - **Verified:** 2026-06-11 ## What it does MCP server built on Resolve's official Scripting API covering project management, media pool, timeline editing, color grading, Fusion comps, Fairlight audio, and the render queue. The most mature NLE MCP available — a filmmaker-agent can conform timelines, apply grades, and kick off renders without touching the GUI. ## Connect - Claude Code: `claude mcp add davinci-resolve -- npx davinci-resolve-mcp setup` - Local: `npx davinci-resolve-mcp setup` **Auth:** local-app — Requires DaVinci Resolve Studio running locally with External Scripting set to Local ## Capabilities `nle-control` · `timeline-editing` · `color-grading` · `compositing` · `render` · `media-management` ## Field notes ~1.2k stars, v2.45.0 (Jun 2026), 78 releases, MIT; 331/336 Resolve API methods live-tested. Requires Resolve STUDIO 18.5+ (the free edition lacks external scripting) and Python 3.10-3.12. The setup wizard auto-configures Claude Desktop/Cursor/VS Code. ## Links - Repo: https://github.com/samuelgursky/davinci-resolve-mcp --- Structured data: https://mcp.film/api/mcps/davinci-resolve.json · Directory: https://mcp.film --- # Deepgram MCP > Official Deepgram server: Nova transcription, diarization, and audio intelligence. - **Category:** Transcription & Captions - **Vendor:** Deepgram (official) - **Pricing:** freemium - **Verified:** 2026-06-11 ## What it does Deepgram's official MCP server gives agents access to its speech platform — fast, accurate transcription with speaker diarization plus audio-intelligence features, with tools fetched dynamically from the API at runtime so new capabilities appear without upgrades. For film work it handles dailies and interview transcription and dialogue logging at production scale. ## Connect - Claude Code: `claude mcp add deepgram -e DEEPGRAM_API_KEY=YOUR_KEY -- deepgram-mcp` - Local: `deepgram-mcp (after `pip install deepgram-mcp`; also bundled with the Deepgram CLI as `dg mcp`)` **Auth:** api_key (env `DEEPGRAM_API_KEY`) — https://console.deepgram.com (free signup credit) ## Capabilities `transcription` · `diarization` · `audio-intelligence` · `tts` ## Field notes Official but young (v0.1.1, Apr 2026). Tool list is fetched from Deepgram's API at runtime; an SSE HTTP mode exists (`deepgram-mcp --transport sse`). Note: AssemblyAI's only official MCP is a docs server, not transcription — Deepgram is the strongest official cloud-STT MCP. ## Links - Site: https://deepgram.com - Docs: https://developers.deepgram.com - Repo: https://github.com/deepgram/mcp --- Structured data: https://mcp.film/api/mcps/deepgram.json · Directory: https://mcp.film --- # Dropbox MCP Server > Dropbox's official remote MCP (beta) for dailies, footage folders, and file ops. - **Category:** Production Ops - **Vendor:** Dropbox (official) - **Pricing:** freemium - **Verified:** 2026-06-11 ## What it does Dropbox's hosted MCP server (beta) connects agents to Dropbox files and folders with OAuth: list, search, upload, download, move, copy, delete, and share, plus content fetch for drafting and summarization. Supports Dynamic Client Registration for trusted clients like Claude and Cursor. ## Connect - Remote endpoint: `https://mcp.dropbox.com/mcp` - Claude Code: `claude mcp add --transport http dropbox https://mcp.dropbox.com/mcp` **Auth:** oauth — Dropbox OAuth consent via mcp.dropbox.com ## Capabilities `file-search` · `upload-download` · `file-ops` · `sharing-links` · `content-fetch` ## Field notes Beta; exact tool names not published on the public help page. A separate official Dash MCP exists for enterprise search (dropbox/mcp-server-dash). Community Go alternative for classic file access: ngs/dropbox-mcp-server (brew install dropbox-mcp-server). ## Links - Site: https://www.dropbox.com - Docs: https://help.dropbox.com/integrations/connect-dropbox-mcp-server --- Structured data: https://mcp.film/api/mcps/dropbox.json · Directory: https://mcp.film --- # ElevenLabs MCP > Official ElevenLabs server: TTS, voice cloning, SFX, music, and dialogue isolation. - **Category:** Voice & Dialogue - **Vendor:** ElevenLabs (official) - **Pricing:** freemium - **Verified:** 2026-06-11 ## What it does The official ElevenLabs MCP server exposes the full audio platform: text-to-speech with thousands of voices, voice cloning and design, text-to-sound-effects, Eleven Music composition, transcription, and audio isolation. For a filmmaker-agent it covers dialogue, SFX, and score from a single API key — the most complete one-stop audio MCP for a film pipeline. ## Connect - Claude Code: `claude mcp add elevenlabs -e ELEVENLABS_API_KEY=YOUR_KEY -- uvx elevenlabs-mcp` - Local: `uvx elevenlabs-mcp` **Auth:** api_key (env `ELEVENLABS_API_KEY`) — ElevenLabs dashboard at elevenlabs.io (free tier: 10k credits/month) ## Capabilities `tts` · `voice-cloning` · `voice-design` · `sfx` · `music` · `transcription` · `audio-isolation` · `speech-to-speech` ## Sample tools `text_to_speech` · `speech_to_text` · `text_to_sound_effects` · `voice_clone` · `text_to_voice` · `isolate_audio` · `compose_music` · `create_composition_plan` · `search_voice_library` · `play_audio` ## Field notes Actively maintained (v0.9.1, Jan 2026, ~1.4k stars); also published as Docker image mcp/elevenlabs and on PyPI. Optional env: ELEVENLABS_MCP_BASE_PATH, ELEVENLABS_MCP_OUTPUT_MODE, ELEVENLABS_API_RESIDENCY. Local stdio only — no hosted remote MCP as of June 2026. ## Links - Site: https://elevenlabs.io - Docs: https://elevenlabs.io/blog/introducing-elevenlabs-mcp - Repo: https://github.com/elevenlabs/elevenlabs-mcp --- Structured data: https://mcp.film/api/mcps/elevenlabs.json · Directory: https://mcp.film --- # fal MCP Server > One hosted endpoint to search, run and chain 1,000+ image, video and audio models. - **Category:** Model Hubs - **Vendor:** fal.ai (official) - **Pricing:** credits - **Verified:** 2026-06-11 ## What it does fal's official stateless MCP server gives agents the entire fal platform: discover models, read schemas and pricing, run inference, submit async jobs and upload files. For filmmakers it is the broadest single gateway — Veo, Kling, LTX-2, Hailuo, FLUX, Ideogram, plus audio like Stable Audio 2.5, CassetteAI SFX and Beatoven — behind one connector. ## Connect - Remote endpoint: `https://mcp.fal.ai/mcp` - Claude Code: `claude mcp add --transport http fal https://mcp.fal.ai/mcp --header "Authorization: Bearer YOUR_FAL_KEY"` **Auth:** api_key (env `FAL_KEY`) — fal.ai dashboard → API Keys (sent as Authorization: Bearer header, never stored server-side) ## Capabilities `text-to-video` · `image-to-video` · `text-to-image` · `image-editing` · `music` · `sfx` · `tts` · `transcription` · `model-search` · `file-upload` · `async-jobs` ## Sample tools `search_models` · `get_model_schema` · `get_pricing` · `run_model` · `submit_job` · `check_job` ## Field notes Hosted and fully stateless; the MCP itself is free, you pay standard fal per-run pricing. Arguably the best single 'everything' server for a generative film pipeline, and the practical MCP route to models with no first-party server (LTX-2, Stable Audio, CassetteAI, Beatoven). ## Links - Site: https://fal.ai - Docs: https://docs.fal.ai/model-apis/mcp --- Structured data: https://mcp.film/api/mcps/fal.json · Directory: https://mcp.film --- # FFmpeg MCP > Conversational FFmpeg: trim, concat, overlay, scale, and extract frames locally. - **Category:** Editing & Post - **Vendor:** Community (video-creator) (community) - **Pricing:** free - **Verified:** 2026-06-11 ## What it does Wraps the FFmpeg CLI as MCP tools for finding, probing, cutting, merging, compositing, and resizing local video files. The workhorse for agent-side post tasks on generated clips — no cloud upload, no credits. ## Connect - Local: `uv --directory /path/to/ffmpeg-mcp run ffmpeg-mcp (after cloning the repo)` **Auth:** none ## Capabilities `transcode` · `trim-concat` · `overlay` · `frame-extraction` · `media-probe` ## Sample tools `find_video_path` · `get_video_info` · `clip_video` · `concat_videos` · `overlay_video` · `scale_video` · `extract_frames_from_video` ## Field notes 134 stars, pushed May 2026 — the best-maintained ffmpeg MCP (egoist/ffmpeg-mcp is dormant since Mar 2025). Caveat: README states macOS only. Cross-platform lighter alternatives: kevinwatt/ffmpeg-mcp-lite and KyaniteLabs/mcp-video (guardrailed, active Jun 2026). ## Links - Repo: https://github.com/video-creator/ffmpeg-mcp --- Structured data: https://mcp.film/api/mcps/ffmpeg.json · Directory: https://mcp.film --- # FLUX MCP > Official BFL server: FLUX.2 text-to-image, editing, multi-reference and variations. - **Category:** Image Generation - **Vendor:** Black Forest Labs (official) - **Pricing:** credits - **Verified:** 2026-06-11 ## What it does Black Forest Labs' official hosted MCP exposes the FLUX.2 toolkit — generation, image editing, multi-reference composition, variations and history — with automatic routing to the right model (Klein for sub-second drafts up to Max for production assets). For filmmakers it is a top-tier stills, concept-art and frame-editing engine inside any agent. ## Connect - Remote endpoint: `https://mcp.bfl.ai` - Claude Code: `claude mcp add --transport http flux https://mcp.bfl.ai` - Local: `npx -y mcp-remote https://mcp.bfl.ai` **Auth:** oauth — OAuth-only: sign in with your BFL account and pick a billing org; tokens auto-refresh ## Capabilities `text-to-image` · `image-editing` · `multi-reference-composition` · `variations` · `generation-history` ## Sample tools `generate_image` · `generate_variations` · `get_history` · `get_credits` ## Field notes Models: flux2_pro_preview (default), flux2_max, flux2_klein variants, flux2_flex (typography). generate_image batches 1-8 images in parallel. Pricing at bfl.ai/pricing. ## Links - Site: https://bfl.ai - Docs: https://docs.bfl.ml/api_integration/mcp_integration - Repo: https://github.com/black-forest-labs/flux-mcp --- Structured data: https://mcp.film/api/mcps/flux-bfl.json · Directory: https://mcp.film --- # Frame.io MCP (community plugin) > 74 tools for Frame.io V4 review workflows — comments, shares, versions, uploads. - **Category:** Review & Distribution - **Vendor:** Community (bowlofarugula) (community) - **Pricing:** freemium - **Verified:** 2026-06-11 ## What it does Python MCP server for the Frame.io v4 API packaged as a Claude Code plugin: browse workspaces and projects, upload/download footage, leave timestamped review comments, create client review links, manage version stacks, apply metadata in bulk, and manage webhooks. Review-and-approval is the connective tissue of film delivery, and this is currently the most complete MCP for it. ## Connect - Claude Code: `claude mcp add frameio -- uvx frameio-mcp serve` - Local: `uvx frameio-mcp serve` **Auth:** oauth — Adobe OAuth (browser one-time login); requires a Frame.io account linked to an Adobe ID ## Capabilities `review-comments` · `share-links` · `version-stacks` · `asset-upload` · `metadata` · `webhooks` ## Field notes Brand new (Jun 2026), Apache-2.0, unproven but functional-looking. Adobe ships no polished official Frame.io MCP — the auto-generated 'V4 Developer MCP Server' on the API docs reportedly gets stuck loading tools with IMS auth issues. Watch this space. ## Links - Site: https://frame.io - Repo: https://github.com/bowlofarugula/frameio-plugins --- Structured data: https://mcp.film/api/mcps/frameio.json · Directory: https://mcp.film --- # Freesound MCP Server > Search freesound.org's 600k+ CC-licensed sounds by natural language for SFX pulls. - **Category:** Sound Design & SFX - **Vendor:** Community (johnkimdw) (community) - **Pricing:** free - **Verified:** 2026-06-11 ## What it does Community MCP server for the Freesound.org API: agents search real recorded sound effects, ambiences, and loops with natural-language queries and get back duration, tags, license info, and preview URLs. For a film pipeline this covers the classic library-pull workflow ('thunder for a storm scene, under 30s') with proper license metadata, complementing generative SFX tools. ## Connect - Local: `uv run freesound-mcp (after cloning the repo and `uv sync`)` **Auth:** api_key (env `FREESOUND_API_KEY`) — https://freesound.org/api/apply/ ## Capabilities `sfx-search` · `audio-metadata` · `license-info` · `preview-urls` ## Sample tools `search_sounds` ## Field notes MIT, small, search-only (no in-tool download); install from source or Docker. Alternatives: MuShan-bit/freesound-mcp (adds download by sound ID) and timjrobinson/FreesoundMCPServer (Node.js). Check individual sound licenses (some CC-BY/NC) before use in a film. ## Links - Site: https://freesound.org - Repo: https://github.com/johnkimdw/freesound-mcp-server --- Structured data: https://mcp.film/api/mcps/freesound.json · Directory: https://mcp.film --- # Google Drive MCP > Google's official remote Drive MCP: search, read, and create files with Workspace governance. - **Category:** Production Ops - **Vendor:** Google (official) - **Pricing:** freemium - **Verified:** 2026-06-11 ## What it does A first-party hosted MCP endpoint from the Drive API team that lets agents search files, read content as a natural-language representation, retrieve metadata, and create/download files — inheriting the user's Drive permissions and Workspace data governance. The production file server for dailies, exports, and shared media. ## Connect - Remote endpoint: `https://drivemcp.googleapis.com/mcp/v1` - Claude Code: `claude mcp add --transport http google-drive https://drivemcp.googleapis.com/mcp/v1` **Auth:** oauth — Bring your own Google Cloud OAuth client (consent screen + client ID/secret) — see the configure-mcp-server guide ## Capabilities `file-search` · `file-read` · `file-create` · `metadata` · `permission-aware` ## Sample tools `search_files` · `read_file_content` ## Field notes Part of the Google Workspace Developer Preview Program — flag as preview. The old Anthropic reference gdrive server is archived; don't use it. Broader community alternative covering Docs/Sheets/Slides/Gmail too: taylorwilsdon/google_workspace_mcp (2.6k stars, very active, uvx workspace-mcp). ## Links - Site: https://drive.google.com - Docs: https://developers.google.com/workspace/drive/api/guides/configure-mcp-server --- Structured data: https://mcp.film/api/mcps/google-drive.json · Directory: https://mcp.film --- # Google GenMedia MCP > Google Cloud's MCP servers for Veo, Imagen, Lyria, Chirp TTS and ffmpeg compositing. - **Category:** Video Generation - **Vendor:** Google Cloud (official) - **Pricing:** paid - **Verified:** 2026-06-11 ## What it does A suite of Go-based MCP servers from Google Cloud's GenMedia Creative Studio repo: Veo text/image-to-video, Imagen and Gemini Image stills, Lyria music, Chirp 3 TTS, and an AVTool server wrapping ffmpeg for compositing. The closest thing to an official Veo MCP, and a full agentic production toolchain on Vertex AI. ## Connect - Follow the vendor's instructions: https://github.com/GoogleCloudPlatform/vertex-ai-creative-studio/blob/main/experiments/mcp-genmedia/mcp-genmedia-go/README.md **Auth:** api_key (env `GOOGLE_CLOUD_PROJECT`) — Google Cloud project with Vertex AI enabled; uses Application Default Credentials (gcloud auth application-default login) ## Capabilities `text-to-video` · `image-to-video` · `text-to-image` · `music` · `tts` · `av-compositing` ## Sample tools `veo_t2v` · `veo_i2v` · `imagen_t2i` · `lyria_generate_music` · `chirp_tts` · `list_chirp_voices` ## Field notes Official Google Cloud code but explicitly experimental (lives in /experiments). Install via the Go toolchain or their pre-built binary installer; supports stdio/HTTP/SSE and GCS or local output. Ships 'genmedia-producer' agent skills for storyboarding. ## Links - Site: https://ai.google.dev/gemini-api/docs/video - Docs: https://github.com/GoogleCloudPlatform/vertex-ai-creative-studio/blob/main/experiments/mcp-genmedia/mcp-genmedia-go/README.md - Repo: https://github.com/GoogleCloudPlatform/vertex-ai-creative-studio/tree/main/experiments/mcp-genmedia --- Structured data: https://mcp.film/api/mcps/google-genmedia.json · Directory: https://mcp.film --- # Google Workspace MCP > Full Google Workspace control — Drive, Docs, Sheets, Slides, Gmail, Calendar and more. - **Category:** Production Ops - **Vendor:** Community (taylorwilsdon) (community) - **Pricing:** free - **Verified:** 2026-06-11 ## What it does The most comprehensive community Workspace MCP, covering 12 Google services with OAuth 2.0/2.1 multi-user support and tool tiers. For film teams: Drive media file search/read/share plus Docs (scripts), Sheets (budgets and shot lists), Slides (pitch decks), Gmail, and Calendar — one server for the whole production office. ## Connect - Claude Code: `claude mcp add google-workspace -e GOOGLE_OAUTH_CLIENT_ID=YOUR_ID -e GOOGLE_OAUTH_CLIENT_SECRET=YOUR_SECRET -- uvx workspace-mcp --tool-tier core` - Local: `uvx workspace-mcp --tool-tier core` **Auth:** oauth (env `GOOGLE_OAUTH_CLIENT_ID`) — OAuth client from Google Cloud Console (https://console.cloud.google.com/apis/credentials) ## Capabilities `drive-files` · `docs` · `sheets` · `slides` · `gmail` · `calendar` · `permissions` ## Sample tools `search_drive_files` · `get_drive_file_content` · `create_drive_file` · `create_doc` · `modify_sheet_values` · `send_gmail_message` · `manage_event` ## Field notes 2.6k stars, 87 releases, MIT, very active. Tool tiers keep the context small (--tool-tier core). npx-only Drive-focused alternative: piotr-agier/google-drive-mcp (166 stars, Apr 2026). ## Links - Repo: https://github.com/taylorwilsdon/google_workspace_mcp --- Structured data: https://mcp.film/api/mcps/google-workspace.json · Directory: https://mcp.film --- # Hedra MCP Server > Character-3 talking-avatar video, TTS, and image generation through Hedra's API. - **Category:** Avatars & Performance - **Vendor:** Community (pasie15) (community) - **Pricing:** credits - **Verified:** 2026-06-11 ## What it does Node MCP server for Hedra's generation API: lip-synced character video from an image plus audio (Character-3), text-to-speech, image generation, and asset/credit management. Also routes to third-party models available in Hedra Studio (Veo 3.1, Sora 2, Kling, MiniMax). ## Connect - Claude Code: `claude mcp add hedra -e HEDRA_API_KEY=YOUR_KEY -- npx -y mcp-server-hedra` - Local: `npx -y mcp-server-hedra` **Auth:** api_key (env `HEDRA_API_KEY`) — https://www.hedra.com/api-profile (requires Creator plan or above) ## Capabilities `avatar-video` · `lip-sync` · `tts` · `text-to-image` · `asset-management` ## Sample tools `generate_video` · `generate_video_with_tts` · `generate_text_to_speech` · `generate_image` · `upload_asset` · `get_generation_status` · `get_credits` ## Field notes New (Feb 2026), MIT, minimal adoption so far; no official Hedra MCP exists. Requires Node 18+. Hedra API access requires a paid Creator plan and API credits. ## Links - Site: https://www.hedra.com - Docs: https://www.hedra.com/docs/pages/developer/getting_started/quickstart - Repo: https://github.com/pasie15/mcp-server-hedra --- Structured data: https://mcp.film/api/mcps/hedra.json · Directory: https://mcp.film --- # HeyGen Remote MCP > Hosted MCP for avatar videos, lipsync, and 175-language video translation. - **Category:** Avatars & Performance - **Vendor:** HeyGen (official) - **Pricing:** credits - **Verified:** 2026-06-11 ## What it does HeyGen's official hosted MCP endpoint lets agents create and manage HeyGen videos with no local install and no API key — auth is a one-time OAuth flow tied to your HeyGen account. Covers Video Agent one-prompt generation, video translation (audio-only or lip-synced, 175+ languages), lipsync jobs, and Photo Avatar / Digital Twin creation, using any custom avatar or voice in your account. ## Connect - Remote endpoint: `https://mcp.heygen.com/mcp/v1/` - Claude Code: `claude mcp add --transport http heygen https://mcp.heygen.com/mcp/v1/` **Auth:** oauth — One-time browser OAuth tied to your HeyGen account ## Capabilities `avatar-video` · `lip-sync` · `video-translation` · `digital-twin` · `voice-library` ## Field notes Available on all HeyGen plans; generation consumes plan credits. HeyGen's legacy stdio package (heygen-mcp) is abandoned — the repo 404s; the maintained community fork is sbroenne/heygen-mcp (uvx heygen-mcp-sbroenne with HEYGEN_API_KEY) if you need a local server. HeyGen also ships official Agent Skills (heygen-com/skills). ## Links - Site: https://www.heygen.com/model-context-protocol - Docs: https://developers.heygen.com/mcp/overview --- Structured data: https://mcp.film/api/mcps/heygen.json · Directory: https://mcp.film --- # Higgsfield MCP > Hosted connector to 30+ video/image models: Kling 3, Veo 3, Sora 2, Soul, Seedance. - **Category:** Video Generation - **Vendor:** Higgsfield AI (official) - **Pricing:** credits - **Verified:** 2026-06-11 ## What it does Higgsfield's official hosted MCP (launched April 2026) exposes its full platform — 30+ models including Kling 3, Veo 3, Sora 2, Seedance, Wan, Hailuo and its own Soul/Cinema Studio — through one endpoint. Agents can generate 4K images, videos up to 15s, train consistent characters and browse creation history on existing Higgsfield plan credits. ## Connect - Remote endpoint: `https://mcp.higgsfield.ai/mcp` - Claude Code: `claude mcp add --transport http higgsfield https://mcp.higgsfield.ai/mcp` **Auth:** oauth — Sign in with your Higgsfield account during connector setup — no API keys ## Capabilities `text-to-video` · `image-to-video` · `text-to-image` · `character-consistency` · `history-browsing` ## Field notes Works with Claude (web/Cowork/Claude Code) and any MCP client; also ships a CLI and agent skills. Community alternatives exist but the official hosted endpoint is the safe pick. ## Links - Site: https://higgsfield.ai - Docs: https://higgsfield.ai/mcp --- Structured data: https://mcp.film/api/mcps/higgsfield.json · Directory: https://mcp.film --- # Houdini MCP > Drive SideFX Houdini nodes and procedural FX from your agent. - **Category:** 3D, Worlds & VFX - **Vendor:** Community (capoomgit) (community) - **Pricing:** free - **Verified:** 2026-06-11 ## What it does Connects Houdini to MCP clients via a Python plugin and a bridge script: create and wire nodes, build assets, and execute code through natural language. Opens Houdini's procedural FX and sim toolset to agent-driven workflows. ## Connect - Follow the vendor's instructions: see links below **Auth:** local-app — Requires Houdini running with the plugin installed (TCP on localhost:9876) ## Capabilities `3d-scene-control` · `procedural-fx` · `node-graph-authoring` · `python-scripting` ## Field notes 224 stars, MIT, active Jun 2026 but early-stage. Manual install (copy plugin into Houdini scripts dir). Alternatives: healkeiser/fxhoudinimcp. For Cinema 4D, the leading equivalent is ttiimmaacc/cinema4d-mcp (87 stars, early-stage, C4D 2024+, MoGraph/Redshift tools). ## Links - Repo: https://github.com/capoomgit/houdini-mcp --- Structured data: https://mcp.film/api/mcps/houdini.json · Directory: https://mcp.film --- # Hume MCP Server > Official Hume server for Octave TTS — emotionally expressive, acting-directed speech. - **Category:** Voice & Dialogue - **Vendor:** Hume AI (official) - **Pricing:** freemium - **Verified:** 2026-06-11 ## What it does Hume's official MCP server drives Octave, a speech-language model that 'performs' text rather than just pronouncing it, with prompt-directed emotion and delivery. Ideal for film dialogue and narration where acting nuance matters; agents can iterate on takes, save designed voices, and replay prior audio. ## Connect - Claude Code: `claude mcp add hume -e HUME_API_KEY=YOUR_KEY -- npx @humeai/mcp-server` - Local: `npx @humeai/mcp-server` **Auth:** api_key (env `HUME_API_KEY`) — https://platform.hume.ai ## Capabilities `tts` · `voice-design` · `expressive-performance` · `voice-library` ## Sample tools `tts` · `play_previous_audio` · `list_voices` · `save_voice` · `delete_voice` ## Field notes Official, published as @humeai/mcp-server on npm with first-party docs. Smaller tool surface than ElevenLabs/Cartesia (TTS-focused). Octave 2 multilingual model strengthens its case for character performance. ## Links - Site: https://www.hume.ai - Docs: https://dev.hume.ai/docs/text-to-speech-tts/mcp-server - Repo: https://github.com/HumeAI/mcp-server-hume --- Structured data: https://mcp.film/api/mcps/hume.json · Directory: https://mcp.film --- # Ideogram MCP Server > Ideogram 3.0 text-to-image with magic prompt and style refs — strongest text-in-image. - **Category:** Image Generation - **Vendor:** Community (Sunwood AI Labs) (community) - **Pricing:** paid - **Verified:** 2026-06-11 ## What it does Community server for the Ideogram API with Ideogram 3.0 support: magic prompt modes, style references, negative prompts, seeds, 15 aspect ratios and batch generation of up to 8 images. Filmmaker-relevant for title cards, posters and any frame where legible rendered text matters. ## Connect - Claude Code: `claude mcp add ideogram -e IDEOGRAM_API_KEY=YOUR_KEY -- npx @sunwood-ai-labs/ideagram-mcp-server` - Local: `npx @sunwood-ai-labs/ideagram-mcp-server` **Auth:** api_key (env `IDEOGRAM_API_KEY`) — Ideogram account → API settings (ideogram.ai) ## Capabilities `text-to-image` · `magic-prompt` · `style-reference` · `batch-generation` ## Sample tools `generate_image` ## Field notes MIT, small; note the 'ideagram' typo in the package/repo name. No official Ideogram MCP exists; Ideogram v3 is also reachable via the fal and Replicate hub MCPs if you want fewer connectors. ## Links - Site: https://ideogram.ai - Repo: https://github.com/sunwood-ai-labs/ideagram-mcp-server --- Structured data: https://mcp.film/api/mcps/ideogram.json · Directory: https://mcp.film --- # json2video MCP > Render JSON-defined videos in the cloud with the json2video API. - **Category:** Editing & Post - **Vendor:** Community (omergocmen) (community) - **Pricing:** freemium - **Verified:** 2026-06-11 ## What it does Community MCP wrapper for json2video.com: assemble scenes of video, images, text, HTML, voice, and subtitles as JSON and render server-side. Good for agentic batch assembly (social cuts, slates, data-driven edits) without a local NLE. ## Connect - Claude Code: `claude mcp add json2video -e JSON2VIDEO_API_KEY=YOUR_KEY -- npx -y @omerrgocmen/json2video-mcp` - Local: `npx -y @omerrgocmen/json2video-mcp` **Auth:** api_key (env `JSON2VIDEO_API_KEY`) — https://json2video.com ## Capabilities `cloud-render` · `template-video` · `captioning` · `video-assembly` ## Sample tools `generate_video` · `get_video_status` · `create_template` · `list_templates` ## Field notes Early-stage but functional npm package. Notable gap it fills: as of June 2026 none of the big video-API platforms (Shotstack, Creatomate) ship an official MCP — this json2video wrapper is the most usable of the bunch. ## Links - Site: https://json2video.com - Repo: https://github.com/omergocmen/json2video-mcp-server --- Structured data: https://mcp.film/api/mcps/json2video.json · Directory: https://mcp.film --- # Kling MCP > Fullest direct Kling API MCP: video, extend, lip-sync, effects, KOLORS images. - **Category:** Video Generation - **Vendor:** Community (199 Longevity) (community) - **Pricing:** credits - **Verified:** 2026-06-11 ## What it does Community server hitting Kuaishou's official Kling API directly, with 13 tools spanning text/image-to-video, video extension, lip-sync with TTS voices, effects, KOLORS image generation and virtual try-on. The most complete option if you want Kling on your own API account rather than via a hub. ## Connect - Claude Code: `claude mcp add kling -e KLING_ACCESS_KEY=YOUR_KEY -e KLING_SECRET_KEY=YOUR_SECRET -- npx -y mcp-kling@latest` - Local: `npx -y mcp-kling@latest` **Auth:** api_key (env `KLING_ACCESS_KEY`) — https://app.klingai.com/global/dev/api-key ## Capabilities `text-to-video` · `image-to-video` · `video-extension` · `lip-sync` · `video-effects` · `text-to-image` ## Sample tools `generate_video` · `generate_image_to_video` · `extend_video` · `create_lipsync` · `apply_video_effect` · `generate_image` · `get_account_balance` ## Field notes MIT, 30 stars. README documents models through Kling v1.x/v2-master — for Kling 3.0 access today, the Runway, Higgsfield or fal hub MCPs may be fresher. Auto-downloads results locally. ## Links - Repo: https://github.com/199-mcp/mcp-kling --- Structured data: https://mcp.film/api/mcps/kling.json · Directory: https://mcp.film --- # Luma AI MCP Server > Dream Machine API in MCP form: Ray 2 video, Photon images, extend and interpolate. - **Category:** Video Generation - **Vendor:** Community (bobtista) (community) - **Pricing:** paid - **Verified:** 2026-06-11 ## What it does Community Python server for Luma's Dream Machine API v1: text/image-to-video on ray-2 and ray-flash-2, video extension and interpolation, Photon image generation, upscaling, audio addition and credit checks. Luma has no official MCP, so this is the main direct-API option. ## Connect - Claude Code: `claude mcp add luma -- uv run --project /path/to/luma-ai-mcp-server -m luma_ai_mcp_server` - Local: `uv run --project /path/to/luma-ai-mcp-server -m luma_ai_mcp_server` **Auth:** api_key (env `LUMA_API_KEY`) — https://lumalabs.ai/dream-machine/api ## Capabilities `text-to-video` · `image-to-video` · `video-extension` · `interpolation` · `text-to-image` · `upscaling` ## Sample tools `create_generation` · `get_generation` · `list_generations` · `upscale_generation` · `add_audio` · `generate_image` · `get_credits` · `get_camera_motions` ## Field notes MIT but tiny (6 stars) — functional rather than polished; runs from a cloned repo via uv. Luma Ray models are also reachable through fal, Replicate, Runway and PiAPI hub MCPs. ## Links - Docs: https://docs.lumalabs.ai/docs/api - Repo: https://github.com/bobtista/luma-ai-mcp-server --- Structured data: https://mcp.film/api/mcps/luma.json · Directory: https://mcp.film --- # Martini > The film set for AI videos — direct entire productions from your agent. - **Category:** Full-Stack AI Studios - **Vendor:** Martini (C47) (official) - **Pricing:** credits - **Verified:** 2026-06-11 ## What it does Martini is an AI video production platform built for professional filmmakers, and its first-party MCP server is the most complete production surface an agent can drive today: projects, infinite canvases, storyboard nodes, multi-model generation (Veo 3.1, Kling 3.0 Pro, Sora 2 Pro, Hailuo 02, Seedance 1.5, Flux and more), reusable subjects for character/prop consistency across shots, batch shot generation with cost approval, a real timeline editor, frame extraction for shot chaining, and asset upload/download. Over 200 professional films have been made on Martini — aired as TV commercials, shown as artwork, and gone viral. ## Connect - Follow the vendor's instructions: https://www.martini.film/docs/mcp **Auth:** oauth — https://www.martini.film — sign in with your Martini account ## Capabilities `text-to-video` · `image-to-video` · `multi-model-generation` · `character-consistency` · `storyboarding` · `shot-planning` · `canvas-collaboration` · `timeline-editing` · `frame-extraction` · `audio-generation` · `3d-sets` · `asset-management` ## Sample tools `create_project` · `create_canvas` · `get_board_overview` · `create_nodes_and_generate` · `list_models` · `create_subject` · `apply_timeline_edit` · `extract_video_frame` · `upload_asset_init` · `get_job_status` ## Field notes Remote MCP server maintained first-party by Martini (YC-backed). Generation tools require explicit user approval of model, prompt, and estimated cost before spending credits — a thoughtful guardrail for agent-driven production. Connect instructions live at martini.film/docs/mcp. ## Links - Site: https://www.martini.film - Docs: https://www.martini.film/docs/mcp --- Structured data: https://mcp.film/api/mcps/martini.json · Directory: https://mcp.film --- # Meshy MCP Server > Official Meshy MCP — generate, retexture, rig, and animate 3D models via API. - **Category:** 3D, Worlds & VFX - **Vendor:** Meshy AI (official) - **Pricing:** paid - **Verified:** 2026-06-11 ## What it does Meshy's official MCP server with 20 tools spanning text/image-to-3D generation, remeshing, retexturing, rigging, animation, and task management. For filmmakers it turns character and prop creation — including rigged, animatable assets — into an agent call. ## Connect - Claude Code: `claude mcp add meshy -- npx add-mcp @meshy-ai/meshy-mcp-server --env MESHY_API_KEY=msy_YOUR_API_KEY` - Local: `npx add-mcp @meshy-ai/meshy-mcp-server --env MESHY_API_KEY=msy_YOUR_API_KEY` **Auth:** api_key (env `MESHY_API_KEY`) — https://www.meshy.ai/settings/api ## Capabilities `3d-generation` · `text-to-3d` · `rigging` · `animation` · `retexturing` ## Field notes Official (meshy-dev org), v0.3.0 (May 2026), MIT, TypeScript; vendor-maintained. Supports stdio and HTTP transports. API access requires a Meshy Pro plan or higher. ## Links - Site: https://www.meshy.ai - Repo: https://github.com/meshy-dev/meshy-mcp-server --- Structured data: https://mcp.film/api/mcps/meshy.json · Directory: https://mcp.film --- # MiniMax MCP > Official MiniMax server: Hailuo video, image gen, music, TTS and voice cloning. - **Category:** Video Generation - **Vendor:** MiniMax (official) - **Pricing:** paid - **Verified:** 2026-06-11 ## What it does MiniMax's official MCP server exposes Hailuo video generation (MiniMax-Hailuo-02, 6s/10s at 768P/1080P), text-to-image, music generation (music-1.5), and best-in-class multilingual TTS with voice cloning and voice design. One vendor and one key covers both your shots and your dialogue — rare breadth for a single official server. ## Connect - Claude Code: `claude mcp add minimax -e MINIMAX_API_KEY=YOUR_KEY -e MINIMAX_API_HOST=https://api.minimax.io -- uvx minimax-mcp` - Local: `uvx minimax-mcp` **Auth:** api_key (env `MINIMAX_API_KEY`) — https://platform.minimax.io — key region must match MINIMAX_API_HOST (api.minimax.io global / api.minimaxi.com mainland) or auth fails ## Capabilities `text-to-video` · `image-to-video` · `text-to-image` · `tts` · `voice-cloning` · `voice-design` · `music` ## Sample tools `generate_video` · `query_video_generation` · `text_to_image` · `text_to_audio` · `voice_clone` · `voice_design` · `music_generation` · `list_voices` ## Field notes MIT, ~1.5k stars, actively maintained, with an official JS sibling (MiniMax-AI/MiniMax-MCP-JS). MINIMAX_API_RESOURCE_MODE toggles URL vs local-file output; MINIMAX_MCP_BASE_PATH sets the output directory. ## Links - Site: https://www.minimax.io - Docs: https://platform.minimax.io/docs/guides/mcp-guide - Repo: https://github.com/MiniMax-AI/MiniMax-MCP --- Structured data: https://mcp.film/api/mcps/minimax.json · Directory: https://mcp.film --- # Miro MCP > Official Miro MCP — build and read storyboards, frames, and planning boards via AI. - **Category:** Story & Pre-Production - **Vendor:** Miro (official) - **Pricing:** freemium - **Verified:** 2026-06-11 ## What it does Miro's hosted MCP server (public beta) lets agents create and read board content: frames, sticky notes, shapes, text, cards, docs, tables, and diagrams, plus retrieve images and resolve comments. A strong fit for storyboard layouts, shot-planning walls, and mood boards your whole team can see. ## Connect - Remote endpoint: `https://mcp.miro.com/` - Claude Code: `claude mcp add --transport http miro https://mcp.miro.com/` **Auth:** oauth — OAuth 2.1 browser flow, per-team authorization ## Capabilities `storyboarding` · `board-creation` · `diagrams` · `mood-boards` · `comments` · `image-retrieval` ## Field notes Public beta; also installable as a Claude Code plugin (/plugin install miro@miro-ai). Tool schemas live at developers.miro.com — the server itself is the source of truth. Enterprise plans add admin controls. ## Links - Site: https://miro.com/ai/mcp/ - Docs: https://developers.miro.com/docs/miro-mcp - Repo: https://github.com/miroapp/miro-ai --- Structured data: https://mcp.film/api/mcps/miro.json · Directory: https://mcp.film --- # Mux MCP Server > Official Mux MCP: upload, manage, and analyze video via API or hosted remote server. - **Category:** Review & Distribution - **Vendor:** Mux (official) - **Pricing:** freemium - **Verified:** 2026-06-11 ## What it does The official MCP server for the full Mux Video + Mux Data platform: upload videos, create and manage assets and live streams, mint playback IDs, manage webhooks, and query video performance analytics. Available both as a hosted remote at mcp.mux.com (OAuth, pick your environment) and as the @mux/mcp npm package — the strongest official offering in video infrastructure. ## Connect - Remote endpoint: `https://mcp.mux.com` - Claude Code: `claude mcp add --transport http mux https://mcp.mux.com` - Local: `npx -y @mux/mcp@latest` **Auth:** oauth (env `MUX_TOKEN_ID`) — Remote: OAuth via dashboard.mux.com. Local: MUX_TOKEN_ID + MUX_TOKEN_SECRET from dashboard.mux.com → Settings → Access Tokens ## Capabilities `video-hosting` · `asset-upload` · `live-streams` · `playback-ids` · `analytics` · `webhooks` ## Sample tools `docs_search` · `execute` ## Field notes npm @mux/mcp v14.x, Apache-2.0, maintained inside the official mux-node-sdk monorepo. Recent versions use a 'Code Mode' design (docs search + sandboxed code execution against the Mux API) instead of hundreds of per-endpoint tools. Supports resource-filtering query params (e.g. ?resource=video.*); DELETE routes mostly excluded by design. ## Links - Site: https://www.mux.com - Docs: https://www.mux.com/docs/integrations/mcp-server - Repo: https://github.com/muxinc/mux-node-sdk/tree/master/packages/mcp-server --- Structured data: https://mcp.film/api/mcps/mux.json · Directory: https://mcp.film --- # Notion MCP > Notion's hosted MCP: search, read, and write docs, wikis, and databases via OAuth. - **Category:** Production Ops - **Vendor:** Notion (official) - **Pricing:** freemium - **Verified:** 2026-06-11 ## What it does Notion's official hosted MCP server gives agents OAuth-scoped access to a workspace: semantic search (including connected Slack/Drive/Jira with Notion AI), fetch pages and databases, and create/update content using AI-native, Markdown-first tools. The natural home for script drafts, beat sheets, character bibles, and shot lists an agent can read and update. ## Connect - Remote endpoint: `https://mcp.notion.com/mcp` - Claude Code: `claude mcp add --transport http notion https://mcp.notion.com/mcp` - Local: `npx -y @notionhq/notion-mcp-server` **Auth:** oauth — One-click OAuth at mcp.notion.com; local server uses a NOTION_TOKEN integration token instead ## Capabilities `workspace-search` · `page-crud` · `database-crud` · `comments` · `markdown-first` ## Sample tools `notion-search` · `notion-fetch` · `notion-create-pages` · `notion-update-page` · `notion-create-database` · `notion-create-comment` ## Field notes ~18 tools on the hosted server (SSE fallback at mcp.notion.com/sse). The open-source local repo (4.4k stars) is explicitly deprioritized by Notion — prefer the hosted URL. Cross-connector search requires a Notion AI / Business plan. ## Links - Site: https://www.notion.com - Docs: https://developers.notion.com/guides/mcp/get-started-with-mcp - Repo: https://github.com/makenotion/notion-mcp-server --- Structured data: https://mcp.film/api/mcps/notion.json · Directory: https://mcp.film --- # PenShot (story-shot-agent) > Breaks screenplays into shot lists and generates Sora/Veo/Runway-ready video prompts. - **Category:** Story & Pre-Production - **Vendor:** Community (neopen) (community) - **Pricing:** free - **Verified:** 2026-06-11 ## What it does An LLM-powered agent that parses scripts in any format, performs shot-by-shot breakdowns, and emits coherent text-to-video prompts with cross-shot character consistency. Runs as an MCP server, Python SDK, REST API, or LangGraph node — the missing link between a screenplay and a generation pipeline. ## Connect - Claude Code: `claude mcp add penshot -- python -m penshot.mcp_server` - Local: `python -m penshot.mcp_server` **Auth:** api_key — Bring your own LLM API key for the underlying agent (per its docs) ## Capabilities `screenplay-parsing` · `shot-breakdown` · `storyboard-scripts` · `t2v-prompt-generation` · `character-consistency` ## Sample tools `breakdown_script` · `get_task_result` ## Field notes 94 stars, actively updated (Jun 2026); docs are bilingual Chinese/English. Directory finding: no dedicated MCP exists for Final Draft, Celtx, WriterDuet, or Fountain as of June 2026 — script writing itself is best done with your agent directly (Fountain is plain text), stored via the Notion or Google Drive MCPs. ## Links - Docs: https://pengline.cn - Repo: https://github.com/neopen/story-shot-agent --- Structured data: https://mcp.film/api/mcps/penshot.json · Directory: https://mcp.film --- # PiAPI MCP Server > Midjourney in an agent — plus Kling, Luma, Hunyuan, Wan, Suno/Udio via PiAPI. - **Category:** Model Hubs - **Vendor:** Community (PiAPI) (community) - **Pricing:** credits - **Verified:** 2026-06-11 ## What it does TypeScript MCP server over PiAPI's unified API, best known as the practical Midjourney route since Midjourney has no public API or official MCP. Also covers FLUX, Kling video and effects, Luma Dream Machine, Hunyuan/Skyreels/Wan video, Trellis 3D and Suno/Udio music — a budget multi-model hub for film agents. ## Connect - Follow the vendor's instructions: https://piapi.ai/docs **Auth:** api_key (env `PIAPI_API_KEY`) — https://piapi.ai (workspace → key management) ## Capabilities `text-to-image` · `midjourney` · `text-to-video` · `image-to-video` · `music` · `3d-generation` ## Field notes MIT, 70 stars; install is clone + npm build. Caveats: unofficial Midjourney access (ToS gray area) and long video jobs can exceed MCP client timeouts — raise timeouts. Hosted Midjourney alternative: AceDataCloud/MidjourneyMCP. ## Links - Site: https://piapi.ai - Docs: https://piapi.ai/docs - Repo: https://github.com/apinetwork/piapi-mcp-server --- Structured data: https://mcp.film/api/mcps/piapi.json · Directory: https://mcp.film --- # Pika MCP > 'Pikafy' your agent: Pika's video, image, music and voiceover tools in Claude. - **Category:** Video Generation - **Vendor:** Pika Labs (official) - **Pricing:** credits - **Verified:** 2026-06-11 ## What it does Pika's official hosted MCP connects its creative suite — video, image, music, audio and voiceover generation — to Claude and other MCP clients, backed by 42 atomic media tools. An official Claude Code plugin adds curated /pika:podcast, /pika:explainer and /pika:ugc-ads slash commands for end-to-end short-form production. ## Connect - Remote endpoint: `https://mcp.pika.me/api/mcp` - Claude Code: `claude mcp add --transport http pika https://mcp.pika.me/api/mcp` **Auth:** oauth — Log in to your Pika account when authorizing the connector ## Capabilities `text-to-video` · `image-to-video` · `text-to-image` · `audio-generation` · `voiceover` · `video-editing` ## Field notes Part of Pika's 2026 pivot to an agent platform. Skill-driven workflows (podcast/explainer/UGC) make it strong for templated content; per-tool documentation is thinner than Runway or fal. ## Links - Site: https://www.pika.me - Docs: https://www.pika.me/mcp --- Structured data: https://mcp.film/api/mcps/pika.json · Directory: https://mcp.film --- # Recraft MCP Server > Official Recraft server: raster + vector image gen, styles, upscale, backgrounds. - **Category:** Image Generation - **Vendor:** Recraft (official) - **Pricing:** credits - **Verified:** 2026-06-11 ## What it does Recraft's official MCP server (remote endpoint or local npm package) covers text-to-image and image-to-image in raster and SVG, custom style creation, vectorization, background removal/replacement and two upscalers. Uniquely useful for film work needing brand-consistent styles, title/poster art and clean vector assets. ## Connect - Remote endpoint: `https://mcp.recraft.ai/mcp` - Claude Code: `claude mcp add recraft -e RECRAFT_API_KEY=YOUR_KEY -- npx -y @recraft-ai/mcp-recraft-server@latest` - Local: `npx -y @recraft-ai/mcp-recraft-server@latest` **Auth:** api_key (env `RECRAFT_API_KEY`) — https://www.recraft.ai/profile/api (buy API units, generate key) ## Capabilities `text-to-image` · `image-to-image` · `vectorization` · `style-creation` · `background-removal` · `upscaling` ## Sample tools `generate_image` · `image_to_image` · `create_style` · `vectorize_image` · `remove_background` · `replace_background` · `crisp_upscale` · `creative_upscale` ## Field notes v1.6.5; per-image API pricing roughly $0.04-$0.08, vectorize $0.01, creative upscale $0.25. Local mode supports IMAGE_STORAGE_DIRECTORY for saving outputs to disk. ## Links - Site: https://www.recraft.ai/blog/recraft-mcp - Docs: https://www.recraft.ai/docs/mcp-reference/getting-started - Repo: https://github.com/recraft-ai/mcp-recraft-server --- Structured data: https://mcp.film/api/mcps/recraft.json · Directory: https://mcp.film --- # Remotion MCP > Official Remotion docs MCP — grounds agents in the programmatic-video framework. - **Category:** Editing & Post - **Vendor:** Remotion (official) - **Pricing:** free - **Verified:** 2026-06-11 ## What it does Remotion's official MCP server indexes the entire Remotion documentation into a vector store so coding agents can correctly build React-based videos, animated graphics, and captions. It is a knowledge server, not a renderer — pair it with the Remotion CLI for actual rendering. ## Connect - Claude Code: `claude mcp add remotion -- npx @remotion/mcp@latest` - Local: `npx @remotion/mcp@latest` **Auth:** none ## Capabilities `docs-search` · `programmatic-video` · `code-assist` ## Field notes Official; npm @remotion/mcp versioned with Remotion core (v4.0.470, Jun 2026). Currently in test phase, open without authentication. Remotion itself requires a paid company license for teams >3 people. For a Remotion-powered video-making MCP, see gyoridavid/short-video-maker (1.2k stars). ## Links - Site: https://www.remotion.dev - Docs: https://www.remotion.dev/docs/ai/mcp - Repo: https://github.com/remotion-dev/remotion --- Structured data: https://mcp.film/api/mcps/remotion.json · Directory: https://mcp.film --- # Replicate MCP Server > Official remote MCP for discovering and running thousands of models on Replicate. - **Category:** Model Hubs - **Vendor:** Replicate (official) - **Pricing:** paid - **Verified:** 2026-06-11 ## What it does Replicate's official MCP server (remote, plus a self-hostable npm package auto-generated from their HTTP API) lets agents search, compare and run any Replicate model — Veo, Kling, Wan, FLUX, SDXL, LTX and more. Experimental 'code mode' lets the model write sandboxed TypeScript against the Replicate SDK for faster multi-step chains. ## Connect - Remote endpoint: `https://mcp.replicate.com/sse` - Claude Code: `claude mcp add --transport sse replicate https://mcp.replicate.com/sse` - Local: `npx replicate-mcp` **Auth:** api_key (env `REPLICATE_API_TOKEN`) — https://replicate.com/account/api-tokens (remote server stores token via web auth flow) ## Capabilities `text-to-video` · `image-to-video` · `text-to-image` · `model-search` · `predictions` · `upscaling` ## Sample tools `search_models` · `create_predictions` · `list_hardware` ## Field notes Remote server recommended; check mcp.replicate.com for the current endpoint (SSE at launch, streamable-HTTP may follow). The npm package tracks the full HTTP API and is auto-updated. Also a strong route to upscalers (Real-ESRGAN, Topaz-style models) with no first-party MCP. ## Links - Site: https://mcp.replicate.com - Docs: https://replicate.com/docs/reference/mcp - Repo: https://github.com/replicate/replicate-mcp-code-mode --- Structured data: https://mcp.film/api/mcps/replicate.json · Directory: https://mcp.film --- # Runway MCP > Official hosted MCP: Gen-4.5, Seedance, Kling and Veo video from any agent. - **Category:** Video Generation - **Vendor:** Runway (official) - **Pricing:** credits - **Verified:** 2026-06-11 ## What it does Runway's hosted MCP server connects agents like Claude, ChatGPT and Cursor to Runway's full generation stack. It routes requests to Gen-4.5, Seedance 2.0, Kling 3.0, Veo 3.1, GPT Image 2 and Nano Banana Pro depending on your plan, making it a one-stop video tool for filmmaker agents with automatic task polling and media URL delivery. ## Connect - Remote endpoint: `https://mcp.runwayml.com/mcp` - Claude Code: `claude mcp add --transport http runway https://mcp.runwayml.com/mcp` **Auth:** oauth — Hosted MCP authenticates with your Runway account (OAuth). Self-hosted repo uses RUNWAYML_API_SECRET from dev.runwayml.com ## Capabilities `text-to-video` · `image-to-video` · `text-to-image` · `video-upscaling` · `video-editing` ## Sample tools `runway_generateVideo` · `runway_generateImage` · `runway_upscaleVideo` · `runway_editVideo` · `runway_getTask` ## Field notes Hosted server (OAuth, no API key, bills Runway credits) is the flagship; an open-source MIT repo exists for self-hosting. Generated asset URLs from the API expire after 24h — download outputs promptly. ## Links - Site: https://runwayml.com/mcp - Docs: https://help.runwayml.com/hc/en-us/articles/51931843164691-Connecting-to-Runway-MCP - Repo: https://github.com/runwayml/runway-api-mcp-server --- Structured data: https://mcp.film/api/mcps/runway.json · Directory: https://mcp.film --- # Sanzaru (Whisper MCP) > OpenAI Whisper/GPT-4o transcription, audio chat, and TTS in one local MCP server. - **Category:** Transcription & Captions - **Vendor:** Community (TJC-LP) (community) - **Pricing:** paid - **Verified:** 2026-06-11 ## What it does Community MCP server wrapping OpenAI's audio APIs: Whisper and GPT-4o transcription with enhancement templates, interactive 'chat with audio' analysis, format conversion/compression, and OpenAI TTS. A filmmaker-agent can transcribe and interrogate dailies, then generate scratch narration, all against a single OpenAI key. ## Connect - Claude Code: `claude mcp add sanzaru -e OPENAI_API_KEY=YOUR_KEY -e SANZARU_MEDIA_PATH=/absolute/path/to/media -- uvx "sanzaru[all]"` - Local: `uvx "sanzaru[all]"` **Auth:** api_key (env `OPENAI_API_KEY`) — https://platform.openai.com (API keys) ## Capabilities `transcription` · `audio-analysis` · `tts` · `format-conversion` ## Sample tools `transcribe_audio` · `transcribe_with_enhancement` · `chat_with_audio` · `create_audio` · `convert_audio` · `compress_audio` ## Field notes Successor to the widely-listed (now deprecated) arcaputo3/mcp-server-whisper. v0.6.2, Apr 2026, MIT. For fully local/offline transcription: jwulff/whisper-mcp and SmartLittleApps/local-stt-mcp (whisper.cpp, Apple Silicon, diarization). ## Links - Repo: https://github.com/TJC-LP/sanzaru --- Structured data: https://mcp.film/api/mcps/sanzaru.json · Directory: https://mcp.film --- # Sora MCP > Community MCP for OpenAI's Sora 2 API: create, remix and manage video jobs. - **Category:** Video Generation - **Vendor:** Community (Doriandarko) (community) - **Pricing:** paid - **Verified:** 2026-06-11 ## What it does The most-starred community MCP for OpenAI's Sora 2 video API: create videos from text, track job status, list, download and remix generations. OpenAI ships no official Sora MCP as of June 2026, so this is the practical way to put Sora directly in an agent pipeline — or reach Sora via the Runway and Higgsfield hubs. ## Connect - Follow the vendor's instructions: see links below **Auth:** api_key (env `OPENAI_API_KEY`) — https://platform.openai.com/api-keys (account must have Sora API access) ## Capabilities `text-to-video` · `remix` · `job-management` · `auto-download` ## Sample tools `create-video` · `get-video-status` · `list-videos` · `download-video` · `remix-video` · `delete-video` ## Field notes MIT, 211 stars; install is clone + npm install + npm run build (no published npx package); includes stdio and HTTP variants. Alternative: writingmate/sora-2-mcp adds sora-2-pro, 720p-4K, 4-12s durations and FFmpeg merging. ## Links - Repo: https://github.com/Doriandarko/sora-mcp --- Structured data: https://mcp.film/api/mcps/sora.json · Directory: https://mcp.film --- # Stability AI MCP Server > Stability platform API as 12 MCP tools: SD3.5 gen, inpaint, outpaint, upscale. - **Category:** Image Generation - **Vendor:** Community (tadasant) (community) - **Pricing:** freemium - **Verified:** 2026-06-11 ## What it does Community wrapper for Stability AI's hosted REST API: SD3.5 and Core generation plus a deep editing kit — outpainting, search-and-replace, search-and-recolor, background replace with relighting, sketch/style/structure control and fast or creative 4x upscaling. A capable, cheap stills and plate-fixing tool for film agents. ## Connect - Claude Code: `claude mcp add stability -e STABILITY_AI_API_KEY=YOUR_KEY -- npx -y mcp-server-stability-ai` - Local: `npx -y mcp-server-stability-ai` **Auth:** api_key (env `STABILITY_AI_API_KEY`) — https://platform.stability.ai/account/keys (25 free credits, then $0.01/credit) ## Capabilities `text-to-image` · `inpainting` · `outpainting` · `background-removal` · `relighting` · `style-structure-control` · `upscaling` ## Sample tools `generate-image` · `generate-image-sd35` · `outpaint` · `search-and-replace` · `search-and-recolor` · `remove-background` · `replace-background-and-relight` · `upscale-creative` ## Field notes MIT, 83 stars; not affiliated with Stability AI (no official Stability MCP exists). Last release Mar 2025 — aging but the API surface it wraps is stable; per-tool costs $0.01-$0.25. ## Links - Repo: https://github.com/tadasant/mcp-server-stability-ai --- Structured data: https://mcp.film/api/mcps/stability-ai.json · Directory: https://mcp.film --- # SunoMCP (AceDataCloud) > Full Suno workflow via a third-party API: songs, lyrics, stems, extends, personas. - **Category:** Music & Score - **Vendor:** Community (AceDataCloud — not Suno) (community) - **Pricing:** credits - **Verified:** 2026-06-11 ## What it does The most complete Suno bridge available as an MCP server, built on AceDataCloud's Suno API: generate songs from prompts or custom lyrics, extend/cover/remaster tracks, split stems, replace sections, and export WAV/MIDI. Useful for temp score and full songs with vocals — capabilities Suno itself does not expose via any official API or MCP. ## Connect - Claude Code: `claude mcp add suno -e ACEDATACLOUD_API_TOKEN=YOUR_TOKEN -- uvx mcp-suno` - Local: `uvx mcp-suno` **Auth:** api_key (env `ACEDATACLOUD_API_TOKEN`) — https://platform.acedata.cloud ## Capabilities `music` · `lyrics` · `song-extension` · `stems` · `covers` · `vocal-extraction` ## Sample tools `generate_music` · `generate_custom_music` · `extend_music` · `cover_music` · `stems_music` · `generate_lyrics` · `get_wav` · `get_midi` ## Field notes Important caveat: Suno has NO official public API as of 2026 — all Suno APIs/MCPs are unofficial resellers and may violate Suno's ToS; commercial-rights claims cannot be guaranteed. The same applies to all Udio wrappers. For licensed-by-design music, prefer Lyria (Google GenMedia) or Stable Audio via the fal hub. ## Links - Site: https://platform.acedata.cloud - Repo: https://github.com/AceDataCloud/SunoMCP --- Structured data: https://mcp.film/api/mcps/suno-acedata.json · Directory: https://mcp.film --- # Tavus MCP > Phoenix replicas, persona videos, lipsync, and conversational AI via the Tavus API. - **Category:** Avatars & Performance - **Vendor:** Community (rakeshdavid) (community) - **Pricing:** freemium - **Verified:** 2026-06-11 ## What it does Comprehensive community MCP server exposing 25 tools across the full Tavus API: Phoenix replica (digital twin) training, persona management, video generation, real-time conversational video (CVI), lipsync, and speech synthesis. Tavus has no first-party MCP server; this is the most complete open implementation. ## Connect - Local: `Build from source: clone rakeshdavid/Tavus-MCP, npm install && npm run build, then run node build/index.js with TAVUS_API_KEY` **Auth:** api_key (env `TAVUS_API_KEY`) — https://platform.tavus.io ## Capabilities `digital-twin` · `avatar-video` · `conversational-video` · `lip-sync` · `tts` ## Sample tools `create_replica` · `generate_video` · `create_conversation` · `create_persona` · `create_lipsync` · `generate_speech` ## Field notes Install caveat: the README's npm package (tavus-mcp) is NOT actually on npm — install from source or via Smithery. Tavus free developer plan: ~25 min conversational video + 5 min generation. Built on an old MCP SDK version. ## Links - Site: https://www.tavus.io - Docs: https://docs.tavus.io - Repo: https://github.com/rakeshdavid/Tavus-MCP --- Structured data: https://mcp.film/api/mcps/tavus.json · Directory: https://mcp.film --- # Topaz Labs MCP > Official Topaz Labs MCP — enhance and upscale images with Topaz AI models. - **Category:** Upscaling & Enhancement - **Vendor:** Topaz Labs (official) - **Pricing:** credits - **Verified:** 2026-06-11 ## What it does Topaz Labs' own MCP server: send an image, get back an enhanced/upscaled version using 9 Topaz models (Standard V2, Wonder 2, Recover 3, and more), defaulting to auto-upscale to 2K. The official path to Topaz-grade enhancement for stills, plates, and frames in an agent pipeline. ## Connect - Claude Code: `claude mcp add topaz -e TOPAZ_API_KEY=YOUR_KEY -- npx -y @topazlabs/mcp` - Local: `npx -y @topazlabs/mcp` **Auth:** api_key (env `TOPAZ_API_KEY`) — https://developer.topazlabs.com/ ## Capabilities `upscaling` · `image-enhancement` · `denoise` · `restoration` ## Sample tools `image-enhance` ## Field notes Official but brand new, MIT, TypeScript. IMAGE ONLY for now — the README says video is 'not yet supported' via MCP even though Topaz's developer API covers Video AI, Photo AI, and Gigapixel. For Topaz VIDEO upscaling today, use the Topaz models hosted on fal.ai via the fal MCP. Needs a filesystem-capable client (Claude Code, not Claude web chat). ## Links - Site: https://www.topazlabs.com/api - Docs: https://developer.topazlabs.com/ - Repo: https://github.com/TopazLabs/topaz-mcp --- Structured data: https://mcp.film/api/mcps/topaz.json · Directory: https://mcp.film --- # Tripo MCP > Official Tripo MCP — text-to-3D assets generated and imported into Blender. - **Category:** 3D, Worlds & VFX - **Vendor:** Tripo (VAST AI Research) (official) - **Pricing:** credits - **Verified:** 2026-06-11 ## What it does VAST's official MCP server generates 3D assets from natural language via the Tripo API and imports them into Blender through the Tripo Blender addon. Quick path from prompt to set-dressing props and previz geometry. ## Connect - Claude Code: `claude mcp add tripo -- uvx tripo-mcp` - Local: `uvx tripo-mcp` **Auth:** api_key — https://platform.tripo3d.ai ## Capabilities `3d-generation` · `text-to-3d` · `asset-import` · `blender-integration` ## Field notes Official, 186 stars — but ALPHA and slow-moving (last release Apr 2025). Currently scoped to Blender-addon integration (requires the separate Tripo AI Blender Addon). Multi-provider community alternative: mordor-forge/trident-mcp (Tripo+Meshy+Rodin). ## Links - Site: https://www.tripo3d.ai - Repo: https://github.com/VAST-AI-Research/tripo-mcp --- Structured data: https://mcp.film/api/mcps/tripo.json · Directory: https://mcp.film --- # Unreal Engine MCP > Control Unreal Engine 5.5+ scenes and Blueprints by natural language. - **Category:** 3D, Worlds & VFX - **Vendor:** Community (Flopperam) (community) - **Pricing:** freemium - **Verified:** 2026-06-11 ## What it does MCP for UE 5.5-5.7 with two modes: a hosted 'Flop MCP' (50+ tools, streamable HTTP) and an open-source local Python server + C++ plugin. Agents can build worlds, author Blueprints, place actors, and set materials and physics — useful for virtual production and previz. ## Connect - Remote endpoint: `https://agent.flopperam.com/mcp` - Claude Code: `claude mcp add --transport http unreal-engine https://agent.flopperam.com/mcp` **Auth:** api_key — https://flopperam.com/account (hosted mode); local mode is free but requires compiling the bundled UnrealMCP C++ plugin ## Capabilities `3d-scene-control` · `blueprint-authoring` · `world-building` · `virtual-production` ## Sample tools `bp_create` · `bp_variable` · `bp_nodes` · `create_town` · `create_castle` ## Field notes 1k+ stars, MIT, actively maintained (May 2026). Landscape note: chongdashu/unreal-mcp is the most-starred (1.9k) but inactive since Apr 2025; ChiR24/Unreal_mcp (699 stars, active Jun 2026) is another option. ## Links - Site: https://flopperam.com - Repo: https://github.com/flopperam/unreal-engine-mcp --- Structured data: https://mcp.film/api/mcps/unreal-engine.json · Directory: https://mcp.film --- # Vimeo MCP Server > Official beta MCP connecting your Vimeo video library to AI agents. - **Category:** Review & Distribution - **Vendor:** Vimeo (official) - **Pricing:** freemium - **Verified:** 2026-06-11 ## What it does Announced at Vimeo's REFRAME conference (Oct 2025) alongside 'Ask Your Library', Vimeo's official MCP server lets agents connect to Vimeo video libraries — list and search videos, read metadata and stats, update titles/descriptions/tags/privacy, and work with transcripts and captions. ## Connect - Follow the vendor's instructions: https://developer.vimeo.com/api/mcp-server **Auth:** oauth (env `VIMEO_ACCESS_TOKEN`) — https://developer.vimeo.com/apps (OAuth app or personal access token with appropriate scopes) ## Capabilities `video-library` · `metadata-editing` · `stats` · `transcripts` · `captions` ## Field notes Beta. The official docs page exists at developer.vimeo.com/api/mcp-server but is gated from crawlers, so the endpoint URL and tool list need manual verification — follow the docs to connect. Community fallback: galacoder/vimeo-mcp (stale, transcript-focused). ## Links - Site: https://www.vimeo.com - Docs: https://developer.vimeo.com/api/mcp-server --- Structured data: https://mcp.film/api/mcps/vimeo.json · Directory: https://mcp.film --- # YouTube MCP Server (data) > Token-optimized YouTube Data API server for video, channel, and trend analytics. - **Category:** Review & Distribution - **Vendor:** Community (kirbah) (community) - **Pricing:** free - **Verified:** 2026-06-11 ## What it does A high-efficiency MCP server returning structured, token-minimized data from the YouTube Data API v3 (claims up to 87% token reduction vs raw API). Covers video details, search, transcripts (at zero quota cost), channel statistics, trending, and outlier-channel discovery — the research side of distribution: study what works before you publish. ## Connect - Claude Code: `claude mcp add youtube -e YOUTUBE_API_KEY=YOUR_KEY -- npx -y @kirbah/mcp-youtube` - Local: `npx -y @kirbah/mcp-youtube` **Auth:** api_key (env `YOUTUBE_API_KEY`) — Google Cloud Console → enable YouTube Data API v3 → Credentials → API key ## Capabilities `video-metadata` · `search` · `transcripts` · `channel-analytics` · `trending` · `comments` ## Sample tools `getVideoDetails` · `searchVideos` · `getTranscripts` · `getChannelStatistics` · `getTrendingVideos` · `getVideoComments` · `findConsistentOutlierChannels` ## Field notes MIT, pushed Jun 2026 — the most actively maintained YouTube data MCP. Read-only (no upload — pair with yutu). Higher-starred alternative: ZubeidHendricks/youtube-mcp-server (530 stars, multi-key quota fallback, ~2.5 months stale). ## Links - Repo: https://github.com/kirbah/mcp-youtube --- Structured data: https://mcp.film/api/mcps/youtube-data.json · Directory: https://mcp.film --- # yutu (YouTube MCP + CLI) > Automate your whole YouTube channel — including real video uploads — via OAuth. - **Category:** Review & Distribution - **Vendor:** Community (eat-pray-ai) (community) - **Pricing:** free - **Verified:** 2026-06-11 ## What it does A Go-based CLI, MCP server, and agent toolkit for YouTube that automates the full workflow: uploading videos, editing metadata, managing playlists, comments, captions, and thumbnails. The only well-maintained MCP option that does real YouTube uploads via OAuth — there is no official Google/YouTube MCP as of June 2026. ## Connect - Claude Code: `claude mcp add youtube-yutu -- yutu mcp` - Local: `yutu mcp` **Auth:** oauth (env `YUTU_CREDENTIAL`) — Google Cloud Console: enable YouTube Data API v3, create an OAuth client, download client_secret.json, then run yutu auth once ## Capabilities `video-upload` · `metadata-editing` · `playlists` · `comments` · `captions` · `thumbnails` · `channel-management` ## Field notes 496 stars, Apache-2.0, pushed Jun 2026 with regular releases. Quota caveat: videos.insert costs 1,600 units → ~6 uploads/day on the default 10k quota, and unverified API projects can only upload private videos until Google audits the project. Lighter upload-only alternative: anwerj/youtube-uploader-mcp. ## Links - Site: https://yutu.ifor.dev - Repo: https://github.com/eat-pray-ai/yutu --- Structured data: https://mcp.film/api/mcps/youtube-yutu.json · Directory: https://mcp.film --- # The AI Film Stack (mcp.film) > Which MCP servers an agent should connect at each stage of making a film. ## Develop Script, beats, boards, plans — spend thought before you spend credits. ### Story & Pre-Production - [Miro MCP](https://mcp.film/mcps/miro.md) (official): Official Miro MCP — build and read storyboards, frames, and planning boards via AI. - [PenShot (story-shot-agent)](https://mcp.film/mcps/penshot.md): Breaks screenplays into shot lists and generates Sora/Veo/Runway-ready video prompts. ## Visualize Stills, concept frames, and start frames that lock the look. ### Image Generation - [FLUX MCP](https://mcp.film/mcps/flux-bfl.md) (official): Official BFL server: FLUX.2 text-to-image, editing, multi-reference and variations. - [Ideogram MCP Server](https://mcp.film/mcps/ideogram.md): Ideogram 3.0 text-to-image with magic prompt and style refs — strongest text-in-image. - [Recraft MCP Server](https://mcp.film/mcps/recraft.md) (official): Official Recraft server: raster + vector image gen, styles, upscale, backgrounds. - [Stability AI MCP Server](https://mcp.film/mcps/stability-ai.md): Stability platform API as 12 MCP tools: SD3.5 gen, inpaint, outpaint, upscale. ## Shoot The virtual cameras: video models, studios, worlds, and performers. ### Full-Stack AI Studios - [Martini](https://mcp.film/mcps/martini.md) (official): The film set for AI videos — direct entire productions from your agent. ### Video Generation - [Google GenMedia MCP](https://mcp.film/mcps/google-genmedia.md) (official): Google Cloud's MCP servers for Veo, Imagen, Lyria, Chirp TTS and ffmpeg compositing. - [Higgsfield MCP](https://mcp.film/mcps/higgsfield.md) (official): Hosted connector to 30+ video/image models: Kling 3, Veo 3, Sora 2, Soul, Seedance. - [Kling MCP](https://mcp.film/mcps/kling.md): Fullest direct Kling API MCP: video, extend, lip-sync, effects, KOLORS images. - [Luma AI MCP Server](https://mcp.film/mcps/luma.md): Dream Machine API in MCP form: Ray 2 video, Photon images, extend and interpolate. - [MiniMax MCP](https://mcp.film/mcps/minimax.md) (official): Official MiniMax server: Hailuo video, image gen, music, TTS and voice cloning. - [Pika MCP](https://mcp.film/mcps/pika.md) (official): 'Pikafy' your agent: Pika's video, image, music and voiceover tools in Claude. - [Runway MCP](https://mcp.film/mcps/runway.md) (official): Official hosted MCP: Gen-4.5, Seedance, Kling and Veo video from any agent. - [Sora MCP](https://mcp.film/mcps/sora.md): Community MCP for OpenAI's Sora 2 API: create, remix and manage video jobs. ### Model Hubs - [ComfyUI MCP](https://mcp.film/mcps/comfyui.md): Drive a local ComfyUI: 40+ tools for image, video, audio and 3D workflows. - [fal MCP Server](https://mcp.film/mcps/fal.md) (official): One hosted endpoint to search, run and chain 1,000+ image, video and audio models. - [PiAPI MCP Server](https://mcp.film/mcps/piapi.md): Midjourney in an agent — plus Kling, Luma, Hunyuan, Wan, Suno/Udio via PiAPI. - [Replicate MCP Server](https://mcp.film/mcps/replicate.md) (official): Official remote MCP for discovering and running thousands of models on Replicate. ### 3D, Worlds & VFX - [Blender MCP](https://mcp.film/mcps/blender.md): The canonical Blender MCP — model, texture, and assemble 3D scenes by prompt. - [ComfyUI MCP (Claude Code plugin)](https://mcp.film/mcps/comfyui-artokun.md): Run and debug ComfyUI workflows from Claude Code — generate, validate, manage VRAM. - [Houdini MCP](https://mcp.film/mcps/houdini.md): Drive SideFX Houdini nodes and procedural FX from your agent. - [Meshy MCP Server](https://mcp.film/mcps/meshy.md) (official): Official Meshy MCP — generate, retexture, rig, and animate 3D models via API. - [Tripo MCP](https://mcp.film/mcps/tripo.md) (official): Official Tripo MCP — text-to-3D assets generated and imported into Blender. - [Unreal Engine MCP](https://mcp.film/mcps/unreal-engine.md): Control Unreal Engine 5.5+ scenes and Blueprints by natural language. ### Avatars & Performance - [D-ID MCP Server](https://mcp.film/mcps/d-id.md) (official): D-ID's hosted MCP connecting agents to the D-ID API and docs for avatar video. - [Hedra MCP Server](https://mcp.film/mcps/hedra.md): Character-3 talking-avatar video, TTS, and image generation through Hedra's API. - [HeyGen Remote MCP](https://mcp.film/mcps/heygen.md) (official): Hosted MCP for avatar videos, lipsync, and 175-language video translation. - [Tavus MCP](https://mcp.film/mcps/tavus.md): Phoenix replicas, persona videos, lipsync, and conversational AI via the Tavus API. ## Sound Dialogue, score, and effects — half the picture is what you hear. ### Voice & Dialogue - [Cartesia MCP](https://mcp.film/mcps/cartesia.md) (official): Official Cartesia (Sonic) server: low-latency TTS, voice cloning, infill, localization. - [ElevenLabs MCP](https://mcp.film/mcps/elevenlabs.md) (official): Official ElevenLabs server: TTS, voice cloning, SFX, music, and dialogue isolation. - [Hume MCP Server](https://mcp.film/mcps/hume.md) (official): Official Hume server for Octave TTS — emotionally expressive, acting-directed speech. ### Music & Score - [SunoMCP (AceDataCloud)](https://mcp.film/mcps/suno-acedata.md): Full Suno workflow via a third-party API: songs, lyrics, stems, extends, personas. ### Sound Design & SFX - [AudioGen MCP](https://mcp.film/mcps/audiogen.md): Free, local sound-effect generation with Meta's AudioGen — no API key needed. - [Auphonic (via Zapier MCP)](https://mcp.film/mcps/auphonic-zapier.md): Auphonic's AI audio post (loudness, leveling, denoise) reachable through Zapier MCP. - [Freesound MCP Server](https://mcp.film/mcps/freesound.md): Search freesound.org's 600k+ CC-licensed sounds by natural language for SFX pulls. ## Cut Assembly, editing, captions: where the film actually gets made. ### Transcription & Captions - [Deepgram MCP](https://mcp.film/mcps/deepgram.md) (official): Official Deepgram server: Nova transcription, diarization, and audio intelligence. - [Sanzaru (Whisper MCP)](https://mcp.film/mcps/sanzaru.md): OpenAI Whisper/GPT-4o transcription, audio chat, and TTS in one local MCP server. ### Editing & Post - [Adobe Premiere Pro MCP](https://mcp.film/mcps/premiere-pro.md): Drive Premiere Pro timelines, effects, and exports from your agent via a CEP bridge. - [After Effects MCP](https://mcp.film/mcps/after-effects.md): Automate After Effects comps, layers, and keyframes through MCP + ExtendScript. - [CapCut MCP](https://mcp.film/mcps/capcut.md): Build CapCut/Jianying draft projects programmatically from an AI agent. - [DaVinci Resolve MCP](https://mcp.film/mcps/davinci-resolve.md): Full AI control of DaVinci Resolve Studio — edit, grade, Fusion, and render via scripting. - [FFmpeg MCP](https://mcp.film/mcps/ffmpeg.md): Conversational FFmpeg: trim, concat, overlay, scale, and extract frames locally. - [json2video MCP](https://mcp.film/mcps/json2video.md): Render JSON-defined videos in the cloud with the json2video API. - [Remotion MCP](https://mcp.film/mcps/remotion.md) (official): Official Remotion docs MCP — grounds agents in the programmatic-video framework. ## Finish Upscale, enhance, and master the delivery files. ### Upscaling & Enhancement - [Topaz Labs MCP](https://mcp.film/mcps/topaz.md) (official): Official Topaz Labs MCP — enhance and upscale images with Topaz AI models. ## Ship Review, publish, distribute — and run the production office. ### Review & Distribution - [Frame.io MCP (community plugin)](https://mcp.film/mcps/frameio.md): 74 tools for Frame.io V4 review workflows — comments, shares, versions, uploads. - [Mux MCP Server](https://mcp.film/mcps/mux.md) (official): Official Mux MCP: upload, manage, and analyze video via API or hosted remote server. - [Vimeo MCP Server](https://mcp.film/mcps/vimeo.md) (official): Official beta MCP connecting your Vimeo video library to AI agents. - [YouTube MCP Server (data)](https://mcp.film/mcps/youtube-data.md): Token-optimized YouTube Data API server for video, channel, and trend analytics. - [yutu (YouTube MCP + CLI)](https://mcp.film/mcps/youtube-yutu.md): Automate your whole YouTube channel — including real video uploads — via OAuth. ### Production Ops - [Airtable MCP Server](https://mcp.film/mcps/airtable.md) (official): Official hosted Airtable MCP: query, create, and update production-tracking bases. - [Dropbox MCP Server](https://mcp.film/mcps/dropbox.md) (official): Dropbox's official remote MCP (beta) for dailies, footage folders, and file ops. - [Google Drive MCP](https://mcp.film/mcps/google-drive.md) (official): Google's official remote Drive MCP: search, read, and create files with Workspace governance. - [Google Workspace MCP](https://mcp.film/mcps/google-workspace.md): Full Google Workspace control — Drive, Docs, Sheets, Slides, Gmail, Calendar and more. - [Notion MCP](https://mcp.film/mcps/notion.md) (official): Notion's hosted MCP: search, read, and write docs, wikis, and databases via OAuth. --- Full registry: https://mcp.film/api/registry.json