ComfyMCP Local
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
ComfyMCP Local
ComfyMCP Local is a local-first MCP server for controlling a loopback-only ComfyUI instance from a same-machine client or an authenticated private-LAN MCP client.
The project starts in disconnected/read-only local_stdio mode with no required
environment variables. HTTP/LAN mode is intentionally fail-closed until TLS,
bearer auth, exact Host admission, and client CIDRs are configured.
By default the ComfyUI upstream must be loopback. To target an HTTPS ComfyUI server on your LAN, opt in explicitly and allowlist the exact upstream host:
COMFYMCP_COMFYUI_URL=https://comfy-gpu.lan.example
COMFYMCP_ALLOW_LAN_COMFYUI=true
COMFYMCP_COMFYUI_ALLOWED_HOSTS=comfy-gpu.lan.exampleLAN upstreams require HTTPS, an origin-only URL, no embedded credentials, and DNS answers that stay inside private LAN address ranges.
npm install
npm run checkUseful development commands:
npm run build
npm test
npm run typecheck
node dist/index.js tools:listThe implementation follows PROJECT_BRIEF.md. Milestone 0 focuses on package
shape, configuration, transport admission policy, authentication primitives,
tool inventory, and fake-ComfyUI test support before porting the full action
services.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Remote MCP server exposing your Node Command fleet (files, shell, processes, browser) to AI hosts.
MCP server for Producer/Riffusion AI music generation
Remote MCP for RunComfy: ComfyUI deployments, hosted models, LoRA training. 31 tools.
Remote MCP server for supportsheep: run AI interviews and manage support content for your blog.
Related MCP Servers
- FlicenseAqualityDmaintenanceMinimal MCP server that wraps ComfyUI HTTP routes enabling LLM clients to inspect server status, models, features, node metadata, submit workflows, manage queue/history, interrupt runs, and upload images.11-
- FlicenseNot gradedqualityDmaintenanceMCP server that connects local ComfyUI to AI agents, enabling natural language control of ComfyUI for creating workflows, generating images, and managing the queue.1-
- FlicenseNot gradedqualityDmaintenanceMCP server exposing a local (or LAN) ComfyUI instance's HTTP API as tools, so an LLM client can queue generations, inspect the queue/history, upload reference images, browse installed models/nodes, and pull back generated images.-
- AlicenseBqualityBmaintenanceMCP server that dynamically exposes each enabled ComfyUI workflow as a tool with JSON Schema, supports job submission with wait and idempotency, file uploads, and resource metadata, with both stdio and authenticated Streamable HTTP transports.36MIT