MCP Utility Kit

MCP Utility Kit

Provides utility tools including random jokes, current weather, and name-based age prediction.

Category
访问服务器

README

MCP Utility Kit

PyPI version Python 3.13+ License: MIT

An MCP (Model Context Protocol) server built with FastMCP that provides three useful daily utility tools:

Tools Provided

  1. Random Joke - Get a random joke of the day
  2. Weather Data - Get current weather using latitude and longitude
  3. Age Prediction - Predict age based on a person's name

Features

  • 🎭 Daily jokes from the Official Joke API
  • 🌤️ Real-time weather data from Open-Meteo
  • 👤 Name-based age prediction from Agify
  • 🚀 Fast and lightweight MCP server
  • 📦 Published on PyPI - ready to use
  • ⚡ No installation needed with uvx

Quick Start

No installation or cloning required! Just add to your MCP configuration and start using.

Prerequisites

  • uv package manager

Install uv:

curl -LsSf https://astral.sh/uv/install.sh | sh

Installation & Setup

Quick Command (Claude CLI)

If you have the Claude CLI installed, add the server with one command:

claude mcp add daily-utils uvx mcp-utility-kit

Option 1: Direct Use with uvx (Recommended)

Use directly without installation:

Add this configuration to your MCP settings file:

VSCode: ~/Library/Application Support/Code/User/mcp.json (Mac) or %APPDATA%\Code\User\mcp.json (Windows)

Claude Desktop: ~/Library/Application Support/Claude/claude_desktop_config.json (Mac)

{
  "mcpServers": {
    "daily-utils": {
      "command": "uvx",
      "args": ["mcp-utility-kit"],
      "type": "stdio"
    }
  }
}

Then reload your MCP client:

  • VSCode: Press Cmd+Shift+P (Mac) or Ctrl+Shift+P (Windows) → "Developer: Reload Window"
  • Claude Desktop: Restart the application

That's it! The server will automatically download and run.

Option 2: Install via pip

If you prefer traditional installation:

pip install mcp-utility-kit

Then run directly:

python -m mcp_utility_kit

Option 3: Local Development Setup

For contributing or modifying the code:

  1. Clone the repository:
git clone https://github.com/thananauto/mcp-utility-kit.git
cd mcp-utility-kit
  1. Install dependencies:
uv sync
  1. Use local configuration in mcp.json:
{
  "mcpServers": {
    "daily-utils": {
      "command": "uv",
      "args": [
        "run",
        "--directory",
        "/full/path/to/mcp-utility-kit",
        "python",
        "-m",
        "mcp_utility_kit"
      ],
      "type": "stdio"
    }
  }
}

Replace /full/path/to/mcp-utility-kit with your local clone path

Usage

Once configured in your MCP client, you can use these tools through your AI assistant:

  • "Tell me a joke" - Gets a random joke
  • "What's the weather in New York?" (provide latitude: 40.7128, longitude: -74.0060)
  • "Predict the age for the name Michael"

Running Standalone in Terminal

# Run directly with uvx (no install needed)
uvx mcp-utility-kit

# Or if installed via pip
python -m mcp_utility_kit

# From local development
uv run python -m mcp_utility_kit

Testing with MCP Inspector

The MCP Inspector provides a web UI for testing:

# Test published version
npx @modelcontextprotocol/inspector uvx mcp-utility-kit

# Test local version
npx @modelcontextprotocol/inspector uv run python -m mcp_utility_kit

This opens a browser interface where you can test all tools interactively.

Available Tools

1. get_joke_of_the_day()

Gets a random joke from the Official Joke API.

Returns: A formatted joke with setup and punchline

Example:

Why did the chicken cross the road?
To get to the other side!

2. get_weather(latitude: float, longitude: float)

Gets current weather data for a location.

Parameters:

  • latitude - Latitude of the location (e.g., 52.52 for Berlin)
  • longitude - Longitude of the location (e.g., 13.41 for Berlin)

Returns: Formatted weather summary with temperature, wind speed, humidity, and weather code

Example:

get_weather(latitude=40.7128, longitude=-74.0060)  # New York City

3. predict_age_by_name(name: str)

Predicts the age associated with a given name using the Agify API.

Parameters:

  • name - First name to predict age for (e.g., "Michael", "Sarah")

Returns: Predicted age and confidence count

Example:

predict_age_by_name(name="Michael")

APIs Used

This server integrates with the following free APIs:

Updating the Package

This package is published on PyPI at: https://pypi.org/project/mcp-utility-kit/

Publishing Updates

To publish a new version:

  1. Update version in pyproject.toml:
version = "0.2.0"  # Increment version number
  1. Build the package:
uv build
  1. Install publishing tools (if not already installed):
uv pip install twine
  1. Upload to PyPI:
uv run twine upload -u __token__ -p YOUR_PYPI_TOKEN dist/*

Get your PyPI token from: https://pypi.org/manage/account/token/

Test Before Publishing

Test on Test PyPI first (optional):

uv run twine upload --repository testpypi -u __token__ -p YOUR_TEST_TOKEN dist/*

Sharing with Team Members

Team members can use this server immediately with no installation:

1. Install uv (if needed)

curl -LsSf https://astral.sh/uv/install.sh | sh

2. Add MCP Configuration

Add to mcp.json (VSCode) or claude_desktop_config.json (Claude Desktop):

{
  "mcpServers": {
    "daily-utils": {
      "command": "uvx",
      "args": ["mcp-utility-kit"],
      "type": "stdio"
    }
  }
}

3. Reload MCP Client

That's it! No cloning, no manual installation needed.

Package Link: https://pypi.org/project/mcp-utility-kit/ Repository: https://github.com/thananauto/mcp-utility-kit

Project Structure

mcp-utility-kit/
├── mcp_utility_kit/
│   ├── __init__.py       # Package initialization
│   ├── server.py         # MCP server implementation with tools
│   └── __main__.py       # Entry point
├── pyproject.toml        # Project configuration and dependencies
├── uv.lock              # Dependency lock file
└── README.md            # This file

Development

Built With

  • FastMCP - Framework for building MCP servers
  • httpx - Async HTTP client for API requests
  • uv - Fast Python package manager

Adding New Tools

To add a new tool to the server:

  1. Open mcp_utility_kit/server.py
  2. Add a new function decorated with @mcp.tool():
@mcp.tool()
async def your_new_tool(param: str) -> str:
    """Tool description for LLM context.

    Args:
        param: Parameter description

    Returns:
        What the tool returns
    """
    # Your implementation here
    return "result"
  1. Test locally with MCP Inspector
  2. Rebuild and republish if deploying to PyPI

Troubleshooting

Server Won't Start

  1. Check uv is installed:

    uv --version
    

    If not installed: curl -LsSf https://astral.sh/uv/install.sh | sh

  2. Test the server directly:

    uvx mcp-utility-kit
    
  3. Check MCP configuration: Ensure mcp.json has the correct format (see Installation section)

  4. View logs: In VS Code, open Output panel (View → Output) and select "MCP" from dropdown

Tools Not Appearing

  • Reload MCP client: In VS Code, press Cmd+Shift+P → "Developer: Reload Window"
  • Check server status: Look for "daily-utils" in the MCP Output logs
  • Verify configuration: Double-check the JSON syntax in your mcp.json

Package Version Issues

To force update to the latest version:

uvx --refresh mcp-utility-kit

API Errors

  • Check internet connection: All three APIs require internet access
  • Rate limits: Free tier APIs may have rate limits
  • Regional restrictions: Verify APIs are accessible from your location

Getting Help

  • Check logs: VS Code Output panel → MCP section shows detailed error messages
  • GitHub Issues: https://github.com/thananauto/mcp-utility-kit/issues
  • MCP Documentation: https://modelcontextprotocol.io/

License

MIT License - see LICENSE file for details

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

Support

For issues and questions:

  • Open an issue in the repository
  • Check existing issues for solutions
  • Review the MCP documentation

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选