ComfyUI MCP
Minimal 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.
README
ComfyUI MCP
Minimal MCP server that wraps ComfyUI HTTP routes so an LLM client can:
- inspect server status, models, features, node metadata
- submit workflows via
/prompt - inspect or manage queue/history
- interrupt runs
- upload input images
Python requirement: 3.10+ (the official mcp SDK requires it).
This server targets ComfyUI local server routes documented in:
- https://docs.comfy.org/development/comfyui-server/comms_routes
- https://docs.comfy.org/development/comfyui-server/api-key-integration
1) Install
cd /Users/apple/projects/comfyui-mcp
python3.10 -m venv .venv
source .venv/bin/activate
pip install -U pip
pip install -e .
2) Configure
export COMFYUI_BASE_URL="http://127.0.0.1:8188"
export COMFYUI_ROUTE_PREFIX=""
export COMFYUI_TIMEOUT_SECONDS="60"
# optional: for reverse proxies or cloud-style gateways
export COMFYUI_BEARER_TOKEN=""
Notes:
COMFYUI_ROUTE_PREFIXcan be set to/apiif your endpoint is exposed only under/api/*.- ComfyUI native server supports both prefixed and non-prefixed routes.
- For paid API nodes in workflow payloads, pass
api_key_comfy_orgincomfyui_submit_prompt.
3) Run (stdio transport)
cd /Users/apple/projects/comfyui-mcp
source .venv/bin/activate
comfyui-mcp
4) Example MCP client config
{
"mcpServers": {
"comfyui": {
"command": "/Users/apple/projects/comfyui-mcp/.venv/bin/comfyui-mcp",
"env": {
"COMFYUI_BASE_URL": "http://127.0.0.1:8188",
"COMFYUI_ROUTE_PREFIX": ""
}
}
}
}
Exposed tools
comfyui_get_system_statscomfyui_get_featurescomfyui_list_modelscomfyui_get_object_infocomfyui_get_queuecomfyui_manage_queuecomfyui_get_historycomfyui_manage_historycomfyui_submit_promptcomfyui_interruptcomfyui_upload_image
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.