comfyui-mcp-server vs filesystem

Side-by-side comparison to help you pick between these two MCP servers.

	comfyui-mcp-server by joenorton	filesystem by modelcontextprotocol
Stars	★ 313	★ 85,748
30d uses	—	—
Score	50	77
Official	—	✓
Categories	AI / LLM ToolsMediaDeveloper Tools	File SystemDeveloper ToolsProductivity
Language	Python	TypeScript
Last commit	3 mo ago	this month

comfyui-mcp-server · Summary

Lightweight Python MCP server for local ComfyUI that enables AI agents to generate and iteratively refine images, audio, and video.

filesystem · Summary

A feature-rich MCP server for filesystem operations with dynamic directory access control.

comfyui-mcp-server · Use cases

AI assistants creating website hero images and logos with precise control
Content generation for social media platforms with iterative refinement
Game asset development with consistent style variations
Music generation from lyrics and tags
Automated media generation for content creators

filesystem · Use cases

Enable AI models to read and write project files during development
Allow Claude or other MCP clients to browse and analyze codebases
Provide secure sandboxed access to specific directories for content generation

comfyui-mcp-server · Install

Quick Installation

1) Clone and install dependencies:

git clone https://github.com/joenorton/comfyui-mcp-server.git
cd comfyui-mcp-server
pip install -r requirements.txt

2) Start ComfyUI locally:

cd <ComfyUI_dir>
python main.py --port 8188

3) Run the MCP server:

python server.py

4) Configure your AI client (e.g., Claude Desktop, Cursor) with:

{
  "mcpServers": {
    "comfyui-mcp-server": {
      "type": "streamable-http",
      "url": "http://127.0.0.1:9000/mcp"
    }
  }
}

filesystem · Install

Installation

Using NPX

{
  "mcpServers": {
    "filesystem": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-filesystem",
        "/path/to/allowed/directory"
      ]
    }
  }
}

Using Docker

{
  "mcpServers": {
    "filesystem": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "--mount", "type=bind,src=/path/to/allowed/dir,dst=/projects/allowed/dir",
        "mcp/filesystem",
        "/projects"
      ]
    }
  }
}

VS Code Extension

Click the installation buttons in the README to install directly in VS Code.

Comparison generated from public README + GitHub signals. Last updated automatically.