File system MCP Server

@iBz-04

Basic information

About File system MCP Server

This is a File system mcp server that could allow an LLM to read and list files from a specified safe directory on your local machine.

#python #open-source #filesystem #mcp #ai-agents #llm #claude-ai #llm-agent #claude-api #model-context-protocol #mcp-server #model-context-protocol-servers #mcp-sdk #python-mcp#claudemcp

File system MCP Server config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "Filesys": {
      "command": "python",
      "args": [
        "-m",
        "venv",
        "venv"
      ]
    }
  }
}

File system MCP Server tools

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.

Overview

What is File system MCP?

File system MCP is a lightweight MCP server built with Python and the mcp library that securely exposes file contents and metadata from a preconfigured directory. It provides endpoints to list files and read file details, and includes an optional integration with Anthropic's Claude AI for natural language interaction.

How to use File system MCP?

Clone the repository, optionally create a virtual environment, install dependencies from requirements.txt, set the Anthropic API key in .env.local, and configure the target directory in config/config.json. Start the server with python run.py, then in a separate terminal run python interact_with_claude.py to chat with Claude, or directly request files://list or files://read/{filename} via any MCP-compatible client.

Key features of File system MCP

List all files in a configurable directory.
Read file contents and metadata (size, last modified).
Integrates with Anthropic Claude for natural language queries.
Validates paths to prevent directory traversal attacks.
Configurable base directory via config/config.json.
Built with Python and FastMCP for lightweight operation.

Use cases of File system MCP

Securely expose a local folder to AI assistants like Claude.
Allow natural language file queries without direct shell access.
Programmatic file listing and reading over the MCP protocol.
Rapid file inspection during development or testing.
Demonstrate MCP server-client interaction with a real file system.

Frequently asked questions

What dependencies does File system MCP require?

Python, the `mcp` library, and optionally the Anthropic SDK for Claude integration (see `requirements.txt`). For Claude usage, an Anthropic API key must be stored in `.env.local`.

Where do the files live?

The server reads from the directory specified in `config/config.json`; the default is `./safe_folder`. Only files within that configured directory are accessible.

How does File system MCP ensure security?

The server validates all file paths and rejects any request that attempts directory traversal, restricting access solely to the configured directory.

What transport does File system MCP use?

It uses the MCP protocol over standard I/O, exposing two resource endpoints: `files://list` and `files://read/{filename}`.

Can I use File system MCP without Claude?

Yes. The MCP server runs independently; you can interact with it via any MCP-compatible client by requesting the built-in file endpoints directly.

Comments

More Files & Storage MCP servers

Sample S3 Model Context Protocol Server

aws-samples

S3 MCP Server

samuraikun

MCP server to integrate AWS S3 and LLM

WORK IN PROGRESS - USE WITH CAUTION - Windows:

hanweg

MCP server for working with PDF files

Filesystem MCP Server SSE

ysthink

The SSE version of the MCP service is modified from the Filesystem MCP server

Filesystem

chrisdoc

Manage your Hevy workouts, routines, folders, and exercise templates. Create and update sessions faster, organize plans, and search exercises to build workouts quickly. Stay synced with changes so your training log is always up to date.

310