What are the required dependencies?
FastMCP, Pydantic, and platform-specific libraries: pywin32 and WMI on Windows only.
@MCP-Mirror
Basic information
Mirror of
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"calebmwelsh_file-system-mcp-server": {
"command": "python",
"args": [
"-m",
"venv",
"venv"
]
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
It's a file system management server built with FastMCP that provides a comprehensive set of tools for file and directory operations. Designed for integration with AI assistants like Claude, it enables automated file management through a structured API.
Clone the repository, create a virtual environment, and install dependencies with pip install -r requirements.txt. For Claude integration, add the server to claude_desktop_config.json using the absolute paths to your Python executable and the fs_server.py script.
FastMCP, Pydantic, and platform-specific libraries: pywin32 and WMI on Windows only.
Add a entry to `claude_desktop_config.json` with the `command` pointing to your Python executable and `args` containing the path to `fs_server.py`. Example for Windows: `"command": "C:\\Users\\YourUsername\\...\\python.exe"`, `"args": ["C:\\Users\\...\\fs_server.py"]`.
The `delete_file` function may fail in some cases, and `list_drives` may not detect all drives correctly. Windows-specific features are unavailable on macOS/Linux.
Collections are stored in a user-specified directory. If no location is given, they default to `data/collections` within the project folder.
Yes, basic file and directory operations are supported. Windows-specific features (drive listing, special folders, detailed system info) are not available on macOS/Linux.
A Model Context Protocol (MCP) server for platform-agnostic file capabilities, including advanced search/replace and directory tree traversal

AI tools (Claude, ChatGPT, Gemini, Grok, etc.) generate HTML constantly, from reports to landing pages to prototypes, but there's no easy way to share it or know if anyone looked. HTMLvault turns any HTML into a clean, t
Model Context Protocol (MCP) Server for reading from Google Drive and editing Google Sheets
MCP Server for reading many files at the same time
The SSE version of the MCP service is modified from the Filesystem MCP server
Comments