mcp.film

MCP serverSearch

This integration gives your AI access to a curated directory of tools for AI filmmaking. Once added, it can search that directory and plan a complete production stack for your project, so you spend less time hunting for the right tools.

Use mcp.film in Claude, ChatGPT or Ahel Desktop

Free. Sign in, add mcp.film and connect your AI. About a minute.

Also: Claude Code · Cursor · Codex

Then ask your AI: use mcp.film to search film mcps

Details

Available today. Use it from your connected AI after setup.

Add the integration, then tell your AI about the film or video you want to make. Ask it to search the directory and put together a production stack for you.

mcp.filmStart free

What your AI can do with it

  • Search a curated directory of AI filmmaking tools
  • Find integrations that match a specific filmmaking need
  • Plan a full production stack for a film project
  • See what tools are available before choosing a setup

Install mcp.film

The server’s own address, for the clients that take one directly. Or connect Ahel once and every client you use reads it from one address, with the account kept on Ahel rather than in each client’s config.

  • Claude Code

    claude mcp add --transport http --scope user mcp-film 'https://mcp.film/mcp'

    Run it once in your project, then open /mcp to approve any sign-in the server asks for.

  • Claude Desktop

    https://mcp.film/mcp

    Add a custom connector in Settings, paste this address, and approve the sign-in.

  • Cursor

    cursor://anysphere.cursor-deeplink/mcp/install?name=mcp-film&config=eyJ1cmwiOiJodHRwczovL21jcC5maWxtL21jcCJ9

    Open the link and Cursor adds the server at that address.

  • ChatGPT

    https://mcp.film/mcp

    In Settings, enable Developer mode, create an MCP app, and paste this address. Your plan and workspace must allow custom apps.

  • Codex

    codex mcp add mcp-film --url 'https://mcp.film/mcp'

    Run it once, then sign in with codex mcp login mcp-film if the server asks for an account.

From the project's README

As published by c47-inc/mcp-film in README.md.

The MCP directory for AI filmmaking. Every tool your agent needs to make a film — video models, voices, scores, edit bays, finishing suites, and the pipes to ship it. Curated, verified, agent-first, and re-checked daily.

🎬 Live site: mcp.film · 🤖 For agents: /llms.txt · /api/registry.json · claude mcp add mcp-film -- npx -y mcp-film


What this is

A directory of verified Model Context Protocol servers across the full film pipeline — from screenplay breakdown to YouTube upload — each entry annotated with exact install commands, auth requirements, pricing, sample tools, and the caveats that actually bite ("requires Resolve Studio", "Suno has no official API", "uploads cost 1,600 quota units").

It is built agents-first:

SurfaceURL
llms.txt index (spec)/llms.txt · /llms-full.txt
Full structured registry/api/registry.json (+ .min.json)
MCP Registry-compatible API/v0.1/servers · /api/mcp-registry.json
Catalog freshness / ops pulse/api/pulse.json · /pulse.md
Production playbooks/api/playbooks.json · /playbooks.md
Agent recommendations/api/recommendations.json · /recommendations.md
Capability index/api/capabilities.json · /capabilities/{tag}.md
Client setup profiles/clients/ · /clients.md · /api/client-profiles.json
One server, JSON / markdown/api/mcps/{slug}.json · /mcps/{slug}.md
Pipeline guide/stack/ · /stack.md
New servers feed/feed.xml
The directory as an MCP servernpx -y mcp-film (packages/mcp-server/)
JSON-LD (SoftwareApplication, ItemList)embedded in every page, server-rendered

How it runs itself

              ┌────────────────────────────────────────────────┐
              │                data/ (the product)             │
              └───────▲────────────────────────────────────────┘
   daily: re-verify   │
   links, hunt new    │
   servers            │
        ┌─────────────┴──┐
        │ curator.yml    │
        │ (Claude agent) │
        └─────────────┬──┘
                      │
                      ▼
              PRs labeled `auto-data` ──► auto-merge.yml
              (merges ONLY if every changed file is in data/
               and validation passes) ──► deploy.yml ──► Cloudflare Pages
                                                     └──► GitHub Pages fallback

Feedback typed on a server page is captured as a PostHog event for a maintainer to read; nothing is folded into the rankings automatically. Rankings are editorial: official status, maintenance recency, hosted availability, and the caveats each entry carries. Every change is a commit — the entire editorial history is auditable.

Agent-readable traffic is measured at the edge when deployed on Cloudflare Pages: the build emits a _worker.js that logs mcpfilm_edge_request events for /llms.txt, markdown, JSON API routes, feeds, and MCP discovery. Browser pageviews still use the lightweight PostHog client event. See docs/ANALYTICS.md.

The live catalog pulse is published at /api/pulse.json and /pulse.md: newest additions, stale verification queue, category coverage, and machine-surface links for agents. Client setup profiles live at /api/client-profiles.json and /clients.md: conservative setup guidance for Claude Code, Claude Desktop, Cursor, hosted remote clients, and the directory's own meta-MCP server.

Production playbooks live at /api/playbooks.json and /playbooks.md: concrete stack recipes with setup order, auth gates, failure modes, and earned Martini handoffs for commercial sprints, local edit bays, character series, archive cutdowns, and open-source labs.

Develop locally

Zero dependencies — Node 20+ is the whole toolchain:

node build.mjs --validate-only   # check the data
node build.mjs                   # build → dist/ (HTML, APIs, feeds, agent surfaces)
node scripts/serve.mjs           # preview at http://localhost:4173

Repo map: data/ is the content, build.mjs + src/ the generator, packages/mcp-server/ the npx mcp-film meta-server, .github/workflows/ the autonomy loop, AGENTS.md the operating manual (for agents and humans alike), docs/SETUP.md the one-time launch checklist, and docs/AGENT_STRATEGY.md the north-star for making the site useful to agents while sending qualified production intent to Martini.

Adding a server

See CONTRIBUTING.md — easiest path is the submission form. A maintainer verifies it against primary sources before it is listed — a submission is a claim, never an instruction.

Who's behind it

Maintained by the team behind Martini, the film set for AI videos — whose MCP server is the featured listing, clearly disclosed. Everything else is ranked on merit: the directory is a community service and its only asset is trust. MIT licensed.

Tools it offers (15)

What this server listed when Ahel dialed its public endpoint in Oct 2026, with no key and no account of yours. The names are the server’s own.

  • search_film_mcps
  • get_film_mcp
  • list_film_categories
  • list_film_capabilities
  • get_film_capability
  • get_install_config
  • list_client_profiles
  • submit_listing
  • get_catalog_pulse
  • list_film_playbooks
  • get_film_playbook
  • list_film_recommendations
  • get_film_recommendation
  • recommend_film_mcps
  • plan_film_stack

Signals

GitHub stars
5
Forks
5
Last commit
Oct 2026
Weekly downloads
56
Advanced
Delivery
directory MCP server → your Ahel connector (mcp.ahel.ai) → your AI.
Item type
mcp-server
Key
film-mcp-directory
Source
github.com/c47-inc/mcp-film
Hosted endpoint
https://mcp.film/mcp