Python (MCP) Filesystem Server

@hypercat

リポジトリ

基本情報

カテゴリ

ファイルとストレージ

トランスポート

stdio

作者

hypercat

Python (MCP) Filesystem Server について

This is a robust Python-based MCP Filesystem Server. It enables AI models and applications to securely interact with the host system's file directories through a defined set of tools, allowing for operations like reading, writing, moving, and listing files and directories.

#filesystem #python #mcp

Python (MCP) Filesystem Server の設定

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": {
    "PyMCP-FS": {
      "command": "uv",
      "args": [
        "pip",
        "install",
        "-r",
        "pyproject.toml"
      ]
    }
  }
}

Python (MCP) Filesystem Server のツール

ツール一覧はまだありません

この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

What is Python (MCP) Filesystem Server?

Python (MCP) Filesystem Server is a Python-based Model Context Protocol (MCP) server that enables AI models and applications to securely interact with host file directories via a defined set of tools. It uses the fastmcp library and confines all file operations to a configurable list of allowed directories.

How to use Python (MCP) Filesystem Server?

Clone the repository and initialize with uv pip install -r pyproject.toml. Run python3 main.py -d /path/to/allowed/dir1 /path/to/another/allowed/dir2 [--log-level LEVEL] [--log-file PATH]. The server listens for MCP messages on stdin and responds on stdout. A test script (test_mcp_server.py) is provided to verify functionality.

Key features of Python (MCP) Filesystem Server

Strict confinement to predefined allowed directories.
Tools for reading, writing, editing, moving, and listing files.
Recursive directory tree generation.
Configurable logging with file rotation.
Symlink validation to prevent path escape.

Use cases of Python (MCP) Filesystem Server

Allowing an AI assistant to read and edit source code in a project directory.
Enabling a chatbot to manage user-uploaded files (e.g., drafts, notes).
Providing controlled filesystem access for automated reporting or data processing tools.
Letting an AI model safely list and inspect files within a sandboxed workspace.

よくある質問

What directories can the server access?

Directories are specified at startup via the `-d` or `--directories` argument. The server will only operate within those paths.

What Python version and dependencies are required?

Python 3.8 or higher is required, along with the `fastmcp` library.

How does the server handle symlinks?

Symlink targets are validated to ensure they do not point outside the configured allowed directories, preventing path escape.

What transport protocol does the server use?

The server uses standard input/output (stdin/stdout) for MCP communication, adhering to JSON‑RPC 2.0 messages.

What logging options are available?

Log level can be set via `--log-level` (DEBUG, INFO, WARNING, ERROR; default INFO). An optional `--log-file` writes logs to a rotating file.

「ファイルとストレージ」の他のコンテンツ

DeviceLink

Jayanka Sampath

DeviceLink lets you share folders from your computer with AI assistants, securely and in real-time. Nothing is uploaded. Your files stay on your machine, and are only accessible while the device sharing them is connected