jay-mcp 0.2.0

MCP server for batch GitHub repository information retrieval with parallel processing

Jay MCP

A demo MCP (Model Context Protocol) server with tools and resources for demonstration purposes.

Features

• Tools: Mathematical operations and server information
• Resources: Personalized greetings and server documentation
• Easy to use: Simple command-line interface
• Extensible: Modular design for easy customization

Installation

From PyPI

pip install jay-mcp

From Source

git clone https://github.com/your-username/jay-mcp.git
cd jay-mcp
pip install -e .

Usage

Command Line

After installation, you can run the MCP server directly:

jay-mcp

This will start the server with stdio transport, which is the standard way to run MCP servers.

Programmatic Usage

You can also use jay-mcp as a library:

from jay_mcp import create_server

# Create a server instance
server = create_server("My Custom Server")

# Run the server
server.run(transport='stdio')

Available Tools

• batch_get_repo_info(repos): 批量获取GitHub仓库信息
  • 参数: repos - 仓库列表，格式：["owner/repo", ...]
  • 返回: 包含仓库详细信息的字典列表
  • 功能: 并行查询多个GitHub仓库的基本信息（stars、forks、语言等）
  • 限制: 单次最多查询50个仓库

Available Resources

• greeting://{name}: Get a personalized greeting
• info://server: Get server information and documentation

Development

Setup Development Environment

git clone https://github.com/your-username/jay-mcp.git
cd jay-mcp
pip install -e ".[dev]"

Running Tests

pytest

Code Formatting

black jay_mcp/
isort jay_mcp/

Type Checking

mypy jay_mcp/

MCP Client Configuration

To use jay-mcp with an MCP client, add this configuration to your MCP settings:

{
  "mcpServers": {
    "jay-mcp": {
      "command": "uvx",
      "args": ["jay-mcp@latest"],
      "description": "Jay MCP Demo Server - Auto-updates to latest version"
    }
  }
}

The @latest tag ensures you always get the newest version automatically.

For a complete configuration example with tool and resource definitions, see mcp_config.json.

Advanced Configuration

You can also create a custom server instance programmatically:

from jay_mcp.server import create_server

# Create a custom server
server = create_server("My Custom MCP Server")

Contributing

1. Fork the repository
2. Create a feature branch
3. Make your changes
4. Add tests if applicable
5. Run the test suite
6. Submit a pull request

License

This project is licensed under the MIT License - see the LICENSE file for details.

Changelog

0.1.0 (2025-07-14)

• Initial release
• Basic MCP server with tools and resources
• Command-line interface
• PyPI package support