mcp-utils

Name: mcp-utils
Author: fulfilio

@fulfilio

リポジトリ

mcp-utils について

Python utilities to work with MCP servers

基本情報

カテゴリ

その他

ライセンス

MIT

ランタイム

python

トランスポート

stdio

公開者

fulfilio

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": {
    "mcp-utils": {
      "command": "npx",
      "args": [
        "-y",
        "@smithery/cli",
        "install",
        "mcp-proxy",
        "--client",
        "claude"
      ]
    }
  }
}

ツール

ツールは検出されませんでした

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 mcp-utils?

mcp-utils is a Python utility package for building Model Context Protocol (MCP) servers, focused on synchronous implementations using Flask. It provides helpers, decorators, and Pydantic models for developers integrating MCP into existing Python applications without asynchronous code.

How to use mcp-utils?

Install with pip install mcp-utils. Create an MCPServer instance, decorate handlers with @mcp.tool() or @mcp.prompt(), and handle incoming requests via mcp.handle_message(). For production, deploy with Flask and Gunicorn.

Key features of mcp-utils

Synchronous MCP server implementation
Server-Sent Events (SSE) support
Simple decorators for tools and prompts
HTTP protocol with Streamable HTTP support
Redis response queue for message handling
Comprehensive Pydantic models for MCP schema
Built-in validation and documentation

Use cases of mcp-utils

Embedding MCP capabilities into existing Python web applications
Building MCP servers with synchronous database transactions (e.g., SQLAlchemy)
Deploying MCP servers with Gunicorn for production workloads
Prototyping MCP tools and prompts without async complexity

FAQ from mcp-utils

What are the runtime dependencies?

Python 3.10+ and Pydantic 2 are required. Flask, Gunicorn, and Redis are optional for web server, production deployment, and response queuing respectively.

Does mcp-utils support asynchronous code?

No, mcp-utils is explicitly designed for synchronous implementations. For async MCP servers, consider the MCP Python SDK.

How do I connect Claude Desktop to an mcp-utils server?

Claude Desktop does not natively support SSE/HTTP; use mcp-proxy (installable via PyPI or Smithery) to bridge stdio with the server's SSE endpoint.

Can I use mcp-utils with Flask for production?

Yes, the README provides Flask examples with Streamable HTTP and optional SQLAlchemy transaction handling, plus a Gunicorn deployment example.

How can I test my MCP server built with mcp-utils?

Use the MCP Inspector (npm install -g @modelcontextprotocol/inspector) to open a web interface, point it to your server’s SSE URL, and send test messages.