RunComfy MCP

claude mcp add runcomfy \ --transport streamable-http \ https://mcp.runcomfy.com/mcp \ --header "Authorization: Bearer <YOUR_RUNCOMFY_TOKEN>"

{ "mcpServers": { "runcomfy": { "url": "https://mcp.runcomfy.com/mcp", "headers": { "Authorization": "Bearer <YOUR_RUNCOMFY_TOKEN>" } } } }

{ "mcpServers": { "runcomfy": { "serverUrl": "https://mcp.runcomfy.com/mcp", "headers": { "Authorization": "Bearer <YOUR_RUNCOMFY_TOKEN>" } } } }

MCP Client ──Bearer token──> Cloudflare Worker (/mcp) │ ▼ Cloudflare Container (Python FastMCP app) │ ▼ api.runcomfy.net (using caller's token)

- Cloudflare Worker(src/index.ts) — thin proxy: CORS, body size check, forwards the caller's token to the container. No auth logic —api.runcomfy.nethandles authentication.
- Python container(server.py) — FastMCP app with 10 tools. Uses the caller's token (forwarded viax-runcomfy-user-tokenheader) for all outbound API calls. Each user sees only their own deployments.
- Cloudflare Containerauto-starts on first request, sleeps after 10 minutes idle.

src/index.ts Cloudflare Worker entrypoint server.py MCP tool definitions (10 tools) runcomfy_client.py RunComfy API client (serverless endpoints) container_app.py ASGI middleware (request IDs, token forwarding) container_entrypoint.py Uvicorn startup container_runtime.py Env validation, structured logging wrangler.jsonc Cloudflare Worker + Container config Dockerfile Container image .env.example Local dev config

# Python 3.11+ python3.11 -m venv .venv source .venv/bin/activate pip install -r requirements.txt cp .env.example .env # Set RUNCOMFY_API_KEY in .env python -m container_entrypoint

- http://127.0.0.1:8000/healthz
- http://127.0.0.1:8000/mcp

In local mode (no Worker), the Python app usesRUNCOMFY_API_KEYfrom.envfor all outbound calls.

Requires Cloudflare Workers Paid plan with Containers enabled.

npm install # Set the API key secret (one-time) npx wrangler secret put RUNCOMFY_API_KEY # Deploy CLOUDFLARE_ACCOUNT_ID=<your-account-id> npx wrangler deploy

The MCP endpoint goes live athttps://mcp.runcomfy.com/mcp(custom domain configured inwrangler.jsonc).

Worker secrets (set viawrangler secret put)

AI Video, Image & Audio Generation with over 150 models

Create, edit, and export SVGator animations (SVG, Lottie, GIF, video) from your AI assistant, and keep an editable project you can open in the editor anytime.

You're agent can Chain 60+ AI image and video models on one workflow canvas

Hosted remote MCP server for AI image and video generation from one Streamable HTTP endpoint.

Generate and edit on-brand images, video, audio, and 3D from any MCP-compatible AI assistant.

Turns public data (World Bank, IMF, FRED, Eurostat, SEC filings) or your own CSV into an animated chart video, recomputing every figure from the source rows before export.

Interact with MiniMax's powerful Text-to-Speech, image, and video generation APIs.

Control Adobe After Effects through a standardized protocol, enabling AI assistants and other applications.

An MCP server that allows AI assistants to interact with Adobe After Effects.

Atlas Cloud MCP Server (Image / Video / LLM APIs)