What does this server do?
It connects to a local ComfyUI and provides a note storage system with resources, a summarize-notes prompt, and an add-note tool.
@jonpojonpo
基本情報
what it says on the tin
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"comfy-ui-mcp-server": {
"command": "uv",
"args": [
"sync"
]
}
}
}Adds a new note to the server
A server for connecting to a local ComfyUI. It implements a simple note storage system with resources, prompts, and tools for managing notes.
Install with uv or uvx. Configure the MCP server in the Claude Desktop config file (claude_desktop_config.json). Invoke with "comfy-ui-mcp-server" as the command. Use the "add-note" tool to add notes, and the "summarize-notes" prompt to create summaries with an optional style argument.
note:// URI scheme for accessing individual notesuv publishIt connects to a local ComfyUI and provides a note storage system with resources, a summarize-notes prompt, and an add-note tool.
Add the MCP server configuration to `claude_desktop_config.json`. For published servers, use `uvx comfy-ui-mcp-server`. For local development, use `uv` with the directory path.
MCP servers run over stdio, so debugging is done via the MCP Inspector.
Use the MCP Inspector by running `npx @modelcontextprotocol/inspector uv --directory <path> run comfy-ui-mcp-server`.
Run `uv sync` to sync dependencies, `uv build` to create distributions, then `uv publish` to upload to PyPI. Set PyPI credentials via token or username/password.

See and control a real Windows PC you own — from any MCP client, locally or remotely. Observe (UIA + screenshots), click/type/drag/scroll, launch apps, owner Live View. BYOH: your machine, your key.

Connect your AI assistant to your own YOUB endurance training account. Read recorded activities with full analysis, planned sessions, race goals, wellness (HRV, sleep, resting HR) and your athletic profile. Create or mov

Soar Flight Booking MCP is a remote MCP server available at https://mcp.soar.flights.
YC (S26) | Open Computer History | Continuously record your company computer work, map your workflows, help you find work worth automating, and power your agents' context
🚀 The fast, Pythonic way to build MCP servers and clients.
コメント