● The MCP directory for AI filmmaking
Every tool your agent needs to make a film.
A curated directory of Model Context Protocol servers across the production stack: video models, voices, scores, edit bays, finishing suites, and the pipes to ship it. Every listing carries the date it was last checked and the caveats that bite people.
161 servers114 official87 hosted remote15 categoriesOct 24, 2026 last verified
registry rebuilt Oct 24, 2026 · 161 servers
The film set for AI videos — direct entire productions from your agent.
Martini is the command surface for agentic filmmaking: one MCP connection that puts an entire film set — the latest video models, infinite production canvases,…
Open the listingThis site is machine-first. One request gets you everything:
curl -s https://mcp.film/api/registry.json
Or start at brief router · /llms.txt · agent recommendations · full agent docs
New to the catalog
6Freshly verified additions from the latest curator passes. Open the catalog pulse.
Local Stable Audio 3 for temp score and SFX: generate, inpaint, extend, loop and loudness-normalize offline.
Official CraftStory server: talking-avatar video from a photo and audio, plus short MiniMax H3 clips with sound.
WaveSpeed's live image, video, audio and 3D catalogue behind seven tools, hosted or via npx.
Brief-to-ad video agent over 100+ models, with a cost estimate before every render.
Search a catalogue of real recordings and buy a lifetime worldwide sync licence per track, WAV plus certificate.
Social publishing and scheduling for YouTube and other channels, with clip jobs that cut long footage into shorts.
Nothing in the catalog matches that. Know a server we're missing? Submit it.
Full-Stack AI Studios
6End-to-end AI film production platforms — generate, organize, and finish entire productions from one MCP connection.
Hosted screenplay-to-production MCP with free planning and quotes, then a greenlit run under a server-enforced cap.
Hosted film lab: storyboard, generate, review, and export, with the price shown before each run.
Hosted AI production studio: projects, shots, voice, music, lip-sync and the cut behind one OAuth connection.
Hosted MCP that carries a script through storyboard, voiceover and shots to a cut MP4.
The film set for AI videos — direct entire productions from your agent.
Open-source desktop workbench your agent directs: storyboard, generate, cut on a timeline.
Generate captioned, lip-synced UGC videos and publish them to social from an agent.
Seedance video, Seedream stills, and Seed Audio behind one typed BytePlus MCP server.
Hosted MCP for a story-to-video studio: multi-shot narrated films, labs, and shorts.
Google Cloud's MCP servers for Veo, Gemini Omni, Lyria, Chirp TTS and ffmpeg compositing.
Hosted connector to 30+ models: Seedance 2.5, Kling 3, Soul 2.0, Nano Banana Pro.
Animates an old portrait or family photo into a short, subtle HD clip; one tool, one credit per photo.
Official remote MCP that turns a prompt into a scripted, narrated, subtitled cut.
Brief to narrated short film or storyboard animatic from a chat client, rendered on rented GPUs with Seedance.
Fullest direct Kling API MCP: video, extend, lip-sync, effects, KOLORS images.
Kling's own hosted MCP: text and image to video or stills, over OAuth on your Kling credits.
Community MCP with the widest tool surface on Luma's legacy Dream Machine API.
Luma's own two-tool MCP server for Ray video and Photon stills.
Magic Hour's hosted MCP: 44 tools across video, image and voice generation on one connection.
Brief or script in, narrated and captioned MP4 out, over one OAuth endpoint.
Official MiniMax server: Hailuo video, image gen, TTS and voice cloning.
Hosted motion-design agent: a prompt in, a finished animated MP4 out, refined by follow-ups.
Pika's hosted media toolkit: 57 apps and models for video, image, audio and edit, from mcp.pika.art.
Official PixVerse video MCP: text/video, image animation, transitions, lip-sync and SFX.
Hosted short-form studio for AI avatars, product scenes, UGC videos, and social delivery.
Hosted MCP that generates, renders, voices, and publishes short-form video end to end.
Official hosted MCP: Gen-4.5, Seedance, Kling and Veo video from any agent.
Dead: OpenAI's shutdown date for the Videos API and every sora-2 model was 2026-09-24.
Brief-to-ad video agent over 100+ models, with a cost estimate before every render.
Script, voiceover or storyboard to finished video, plus clip, image, music and avatar generation.
Hosted MCP over a multi-model video roster, with avatars, voices, and brand kits.
Exposes whole ad-creative workflows over MCP rather than individual model endpoints.
Image Generation
6Stills, concept frames, storyboards, and start frames for image-to-video pipelines.
Official BFL server: FLUX.2 stills and editing, now with FLUX 3 video generation.
Dead: the official repo is deleted and Freepik's developer platform is now Magnific.
Official Ideogram server: bulk generation, editing, reframe, upscale and model training.
One MCP across Gemini, OpenAI and Kie AI, with EU AI Act disclosure marking built in.
Official hosted Recraft server: raster + vector generation, styles, upscale, backgrounds.
Stability platform API as 12 MCP tools: SD3.5 gen, inpaint, outpaint, upscale.
Model Hubs
22Aggregators exposing hundreds of hosted models — video, image, and audio — through a single MCP connection.
Official hosted Artlist MCP — generate images, video, music and voice-over on your Artlist credits.
One API key over a large image, video, audio and 3D model catalogue, with a dry-run flag.
Hosted OAuth MCP onto BudgetPixel's image, video, music, SFX and Topaz upscale catalogue.
Comfy Org's own MCP: drive your local ComfyUI, or Comfy Cloud, from an agent.
Drive a local ComfyUI: 40+ tools for image, video, audio and 3D workflows.
Remote hub over 180+ hosted models: video, image, speech, 3D, plus GPUs by the hour.
One hosted endpoint to search, run and chain 1,000+ image, video and audio models.
One hosted endpoint over 450 models: text-to-video from Veo, Kling, Seedance and Hailuo on one pay-as-you-go balance.
Foundry's node-based AI workflow engine, drivable by an outside agent over local HTTP.
Hedra's own hosted MCP: one OAuth URL onto its whole image, video and audio catalogue.
One OAuth endpoint onto ImagineArt's video, image and music models — 96 tools, no keys.
Official hosted hub: run any image, video, audio or 3D app, then poll the task.
Run Veo, Seedance, Kling, Runway, Suno, ElevenLabs, FLUX and more through one local MCP.
Official hosted MCP for Krea image/video models, schemas, uploads, and job widgets.
Quote a shot across the video model zoo, then approve the one you want to pay for.
Midjourney in an agent — plus Kling, Luma, Hailuo, Hunyuan, Wan, Suno via PiAPI.
Hosted OAuth MCP for 20+ video, image, audio and 3D models, with a credit preview on every call.
Model intelligence MCP for prompt syntax, pricing, and budget-aware picks.
Official remote MCP for discovering and running thousands of models on Replicate.
Browse, price, and run 130+ image, video, audio and voice models through one MCP.
Official Runware MCP for image, video, audio, 3D, upscaling, and model search.
WaveSpeed's live image, video, audio and 3D catalogue behind seven tools, hosted or via npx.
Voice & Dialogue
6Text-to-speech, voice cloning, and emotionally directed performance for dialogue and narration.
Official voice and video localization MCP: TTS, cloning, dubbing, subtitles.
Hosted MCP for TTS, voice cloning, music, stem and speaker separation, and denoise.
Official Cartesia (Sonic) server: low-latency TTS, cloning, voice change, localization.
Official ElevenLabs server: TTS, voice cloning, SFX, music, and dialogue isolation.
Hosted Fish Audio server: voice search, expressive TTS, transcription, plus image and video generation.
Official Hume server for Octave TTS — emotionally expressive, acting-directed speech.
Composes and arranges inside a running Ableton Live set — tracks, clips, devices, transport.
Search a catalogue of real recordings and buy a lifetime worldwide sync licence per track, WAV plus certificate.
Search a cleared music and SFX catalogue, then download stems, from the agent.
Official Mureka server for lyrics, songs, and instrumental background music.
Watches the footage, then returns license-safe music, a hook window, and a ducking spec.
Score and effects generated against the cut, from a catalogue trained on licensed music.
Full Suno workflow via a third-party API: songs, lyrics, stems, extends, personas.
Local Stable Audio 3 for temp score and SFX: generate, inpaint, extend, loop and loudness-normalize offline.
Local, offline sound-effect generation with Meta's AudioGen — no API key, no credits.
Loudness, true-peak and voice metering that grades a mix against real delivery specs.
Auphonic's automated audio post (loudness, leveling, denoise) reachable through Zapier MCP.
Search freesound.org's CC-licensed sound library by natural language for SFX pulls.
Foley generated against the picture, then extended or patched region by region.
Drives a live REAPER session: tracks, MIDI, FX, mixing, stems, and loudness analysis.
Transcription & Captions
3Speech-to-text, diarization, and dialogue logging for edits, subtitles, and accessibility.
Official Deepgram server: Nova transcription, diarization, and audio intelligence.
Quoted dubbing, subtitles, transcription and multi-voice audiobooks from one remote MCP; a human approves each price.
Whisper and GPT-4o transcription, audio chat, and TTS against one OpenAI key.
Editing & Post
32NLE control (DaVinci Resolve, Premiere), programmatic editing, ffmpeg, and render pipelines.
Adobe's official hosted MCP — 50+ tools across Photoshop, Lightroom, Firefly, Premiere, Express and Stock.
Drive Premiere Pro timelines, effects, and exports from your agent via a CEP bridge.
Adobe's second hosted MCP — compose and run Firefly Creative Production batch pipelines.
Automate After Effects comps, layers, and keyframes through MCP + ExtendScript.
Archived: a CapCut draft-builder whose repo is now read-only — use vectcut instead.
Lets an agent actually watch footage locally — scene-cut keyframes plus transcript, no upload.
Hosted OAuth MCP that builds and edits a real, re-openable timeline by conversation.
Local MCP bridge into DaVinci Resolve that runs on the Free edition, not just Studio.
Full AI control of DaVinci Resolve Studio — edit, grade, Fusion, and render via scripting.
First-party MCP server built into DaVinci Resolve Studio 21.1 — no third-party bridge.
Descript's official hosted MCP — import media, run Underlord edits, publish, from your agent.
Final Cut Pro MCP with FCPXML editing, live control, media QC and Compressor dispatch.
Turn Final Cut Pro XML into QC, markers, rough cuts, and cross-NLE handoffs.
Conversational FFmpeg: trim, concat, overlay, scale, and extract frames locally.
Superseded community wrapper — JSON2Video now ships its own MCP.
The vendor's own MCP: render JSON movies, validate them, and manage the media library.
Guardrailed local video editing MCP — FFmpeg, receipts, quality gates, and repurposing.
Deterministic video from one JSON template — same input, same frames, rendered locally.
A local editor with no GUI and no LLM: an append-only edit graph an agent drives over MCP.
Turns long footage into ranked short clips, then captions, edits, and schedules them.
Local MCP and CLI toolkit for agent-driven video composition, editing, analysis, and rendering.
AI-native Mac timeline editor with a built-in local MCP server — closed source since v0.7.6.
Render After Effects-backed video templates from an agent with Plainly's API.
Hosted MCP that clips, captions, dubs, reframes, and publishes long-form footage.
Remotion's docs MCP, deprecated — the hosted server shuts down no earlier than Aug 31 2026.
Cloud video editing, Studio previews, and template rendering over Shotstack's hosted MCP.
Cross-video agent MCP: build a knowledge store, then ask your whole library questions.
Index, search, and analyze video libraries with Pegasus and Marengo through MCP.
Hosted video-understanding MCP: transcripts, shots, visual scenes, soundbites, and clips.
Assemble CapCut and Jianying draft projects from an agent over a local stdio MCP server.
CLI-first video workflow runtime with an MCP surface for briefs-to-renders.
Search, analyze, and generate edits from source videos through Video Jungle.
Upscaling & Enhancement
3Video upscaling, frame interpolation, denoising, and image enhancement — the finishing suite.
Cloud video upscaling and SAM3 segmentation without a local GPU, billed by the second.
Official remote MCP for upscaling, image/video generation, characters, and asset history.
Official Topaz Labs MCP — enhance and upscale images with Topaz AI models.
Blender's own MCP server — natural-language access to the Blender Python API.
The most-adopted Blender MCP — model, texture, and assemble 3D scenes by prompt.
Maxon's built-in MCP server: drive scenes, variations, multipass renders and sims in Cinema 4D.
Drive ComfyUI as a live image, video, audio, and workflow workbench from your agent.
Drive SideFX Houdini nodes and procedural FX from your agent.
Drive live Autodesk Maya sessions from an agent — arbitrary Python, streamed back.
Official Meshy MCP — generate, retexture, rig, and animate 3D models via API.
The only roto, paint, and planar-tracking MCP — Boris FX Silhouette driven by an agent.
Official Tripo MCP — text-to-3D assets generated and imported into Blender.
Third-party Unreal MCP for UE 5.5+, with a hosted 50-tool option Epic's server has no answer to.
Epic's first-party in-editor MCP server for Unreal Engine 5.8.
Hosted MCP for AKOOL face swap, character swap, image-to-video, TTS and avatar lookup.
Studio MCP for talking avatars, locked recurring characters, and batched output.
Official bitHuman CLI server: build avatar agents from a face image and render WAV-driven talking video locally.
Official CraftStory server: talking-avatar video from a photo and audio, plus short MiniMax H3 clips with sound.
D-ID's hosted MCP connecting agents to the D-ID API and docs for avatar video.
Character-3 talking-avatar video, TTS, and image generation through Hedra's API.
Hosted MCP for avatar videos, lipsync, and 175-language video translation.
Official Sync MCP for lipsync generation, voice cloning, and TTS on existing footage.
Phoenix replicas, persona videos, lipsync, and conversational AI via the Tavus API.
VEED's hosted MCP for talking-head video: pick a character, pick a voice, send a script.
Story & Pre-Production
5Screenwriting, storyboarding, and planning tools for the development phase.
Cinematography reference: search film stills from 5,489 films by lighting, lens, shot size, colour and mood.
Official Miro MCP — build and read storyboards, frames, and planning boards via AI.
Where films and series were actually shot: 31,000+ locations in 177 countries, from Wikidata.
Breaks screenplays into shot lists and generates Sora/Veo/Runway-ready video prompts.
Keeps AI-film characters, locations, shots, and lock status grounded in project files.
Review & Distribution
9Publishing to YouTube and Vimeo, review and approval, and video hosting infrastructure.
Social publishing and scheduling for YouTube and other channels, with clip jobs that cut long footage into shorts.
Official Canva remote MCP for campaign designs, thumbnails, decks, exports, and comments.
Adobe's hosted Frame.io MCP: review comments, shares, version stacks, uploads, and metadata.
74 tools over the Frame.io V4 API — comments, shares, version stacks, uploads.
Official Mux MCP: upload, manage, and analyze video via API or hosted remote server.
Official Vimeo remote MCP: library search, analytics, retention, and metadata editing.
Official Wistia remote MCP: upload, trim, caption, dub, publish, and read the analytics.
Token-optimized YouTube Data API server for video, channel, and trend analytics.
Automate your whole YouTube channel — including real video uploads — via OAuth.
Official hosted Airtable MCP: query, create, and update production-tracking bases.
Official Cloudinary MCP for uploading, organizing, searching, and transforming media assets.
Dropbox's official remote MCP (beta) for dailies, footage folders, and file ops.
Official remote MCP for searching and downloading licensed Getty stills and footage.
Google's official remote Drive MCP: search, read, and create files with Workspace governance.
Full Google Workspace control — Drive, Docs, Sheets, Slides, Gmail, Calendar and more.
Notion's hosted MCP: search, read, and write docs, wikis, and databases via OAuth.
Remote MCP for searching and licensing restored 8mm and Super 8 home-movie footage.
Questions, answered
What is an MCP server?
A standard interface (the Model Context Protocol) that lets AI agents like Claude operate software as tools. For filmmaking, that means your agent can generate shots on Runway, clone a voice on ElevenLabs, or cut a timeline in DaVinci Resolve — through one protocol.
How do I connect one to Claude or Cursor?
Every listing here has copy-paste connect commands for Claude Code, Claude Desktop, and Cursor, plus the auth you'll need. Hosted "remote" servers connect with one command and an OAuth login; local ones run via npx or uvx.
Which video generation MCP should I use?
If you want one connection covering many models, start with a hub like fal or a studio like Martini. If you live on one platform, use its official server — Runway, Higgsfield, and Pika all run hosted MCPs. The Stack walks the whole decision.
I'm an AI agent. What's the fastest way to read this site?
One request: GET /api/registry.json. Or start at /llms.txt; every page has a markdown twin at the same path plus .md. Full details on the agents page.
How do listings stay accurate?
A curator agent re-verifies entries every day against primary sources, and every change lands as an auditable commit in the open-source repo. Each entry shows its last-verified date.
How do I get my MCP server listed?
Humans: the submission form. Agents: the submit_listing tool on npx mcp-film. Either way a maintainer verifies your claims against primary sources — it works, it's filmmaking-relevant, it's maintained.