mini_mcp
Documentation
mini_mcp
mini_mcp is a lightweight plugin built with FastMCP that retrieves the list of all files located on the current macOS user's desktop.
📦 Installation
It is recommended to use Conda to create an isolated environment:
conda create -n mcp python=3.12
conda activate mcp
pip install fastmcpIf you want to install with the requirements.txt file, install dependencies with:
pip install -r requirements.txt⚙️ MCP Configuration
To invoke the list_desktop_files tool from an external MCP client, use the following configuration:
{
"mcpServers": {
"list_desktop_files": {
"command": "/Users/hzq/anaconda/anaconda3/envs/mcp/bin/python",
"args": [
"/Users/hzq/py_projects/mini_mcp/main.py"
]
}
}
}>⚠️ Make sure to update the paths to match your local Python interpreter and project location.
🛠 Tool Description
`list_desktop_files()`
- Purpose: Lists all files and folders on the current user's desktop.
- Platform: macOS only
- Returns: A list of strings, each representing a file or folder name.
Example output
[
"report.pdf",
"screenshot.png",
"MyFolder"
]📁 Project Structure
mini_mcp/
├── main.py # Main script that registers the FastMCP tool
├── README.md # This documentation file
└── requirements.txt # (Optional) Dependency definitions🔒 Notes
- This tool is implemented specifically for macOS due to the use of the `~/Desktop` path.
- To adapt this tool for Windows or Linux, modify the desktop path accordingly in the `main.py` script.
- Ensure that `fastmcp` is installed and compatible with your Python version.
🧩 License
This project is provided as-is without any warranty. For licensing terms, refer to FastMCP’s license if applicable.
Frequently asked questions
What is mini_mcp?
mini_mcp is a Model Context Protocol (MCP) server listed in the TrackMCP directory.
How do I install mini_mcp?
Open the GitHub repository and follow its README. Most MCP servers are added to your client's MCP config, then called by your agent.
Is mini_mcp open source?
Yes — it is hosted on GitHub at https://github.com/tinyzqh/mini_mcp.
Related MCP tools
Cognee is the open-source AI memory platform for agents. Give your AI agents persistent long-term memory across sessions with a self-hosted knowledge graph engine.
Python SQL Parser and Transpiler
MCP server that interacts with Obsidian via the Obsidian rest API community plugin
Open-source meeting transcription API for Google Meet, Microsoft Teams & Zoom. Auto-join bots, real-time WebSocket transcripts, MCP server for AI agents. Self-host or use hosted SaaS.
A super light-weight embedded code search engine CLI (AST based) that just works - improves speed and efficiency for coding agent 🌟 Star if you like it!
Official MiniMax Model Context Protocol (MCP) server that enables interaction with powerful Text to Speech, image generation and video generation APIs.
Run your own MCP server? See who uses it and what to fix.
Measure it with TrackMCP