Tsuki MCP Filesystem Server

@yuutotsuki

リポジトリ

基本情報

カテゴリ

ファイルとストレージ

ライセンス

MIT license

トランスポート

stdio

作者

yuutotsuki

Tsuki MCP Filesystem Server について

A custom MCP-compatible server for searching local filesystem files. Works with OpenAI's Agent SDK via the resources/list method. ローカルファイルの検索を行う、自作のMCP対応サーバーです。 Agent SDK の `resources/list` に対応しています。

Tsuki 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": {
    "tsuki_mcp_filesystem_server": {
      "command": "python",
      "args": [
        "main.py"
      ]
    }
  }
}

Tsuki 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 tsuki_mcp_filesystem_server?

tsuki_mcp_filesystem_server is a custom Model Context Protocol (MCP) server that provides file search and open operations over the local filesystem. It is designed for integration with OpenAI's Agent SDK, enabling AI agents to list and open local files via the resources/list method.

How to use tsuki_mcp_filesystem_server?

Clone the repository, install dependencies with pip install -r requirements.txt, copy .env.example to .env, configure the ROOT_PATH, HOST, PORT, and LOG_LEVEL settings, then start the server with python main.py. The server listens for MCP client requests on the configured host and port.

Key features of tsuki_mcp_filesystem_server

Provides file system resources via MCP protocol
Supports file search and open operations
Automatic MIME type detection
Flexible configuration through environment variables
Implements JSON-RPC protocol

Use cases of tsuki_mcp_filesystem_server

Enabling OpenAI Agent SDK to search and open local files
Exposing a local directory's file list to MCP-compatible clients
Building AI-powered tools that need local filesystem access
Prototyping agentic workflows with file retrieval capabilities

よくある質問

What transport or protocol does tsuki_mcp_filesystem_server use?

It uses the JSON-RPC protocol over TCP/IP, listening on a configurable host and port.

What runtime or dependencies are required?

Python 3 and the packages listed in `requirements.txt` are required.

What configuration is needed before starting the server?

You must set the `ROOT_PATH` environment variable (or in `.env`) to specify the directory to be searched. Optionally, set `HOST`, `PORT`, and `LOG_LEVEL`.

How does this server compare to other MCP file servers?

The README states it is a custom, lightweight server focused on file search and open operations via the `resources/list` method.

Where does the file data live?

The server only accesses files under the configured `ROOT_PATH` directory on the local filesystem. No external storage is used.

「ファイルとストレージ」の他のコンテンツ

mcp-v8: V8 JavaScript MCP Server

r33drichards

MCP server that exposes a V8 JavaScript runtime as a tool for AI agents like Claude and Cursor. Supports persistent heap snapshots via S3 or local filesystem, and is ready for integration with modern AI development environments.

PDF Reader MCP Server (@sylphlab/pdf-reader-mcp)

sylphlab

📄 The PDF intelligence layer for AI agents — Agent Document Twin, evidence-first extraction, visual crops, OCR provenance, trust reports, and benchmark-gated releases. MCP server for Claude, Cursor, VS Code, and any MCP client.

810