Berry MCP Server

Berry MCP Server

A universal framework for creating and deploying custom Model Context Protocol (MCP) tool servers with decorator-based tool registration, supporting multiple transports and automatic JSON schema generation for AI assistants.

Category
访问服务器

README

Berry MCP Server

CI Tests Python 3.10+ License: MIT uv

A universal Model Context Protocol (MCP) server framework that makes it easy to create and deploy custom tool servers for AI assistants like Claude.

✨ Features

  • 🔧 Universal Framework: Create MCP servers for any type of tools
  • 🎯 Simple Tool Creation: Decorator-based tool registration with automatic JSON schema generation
  • 🔌 Plugin Architecture: Load tools from any Python module or package
  • 🚀 Multiple Transports: Support for stdio and HTTP/SSE communication
  • ⚙️ Flexible Configuration: Environment variables and command-line options
  • 📝 Auto-Documentation: Automatic tool discovery and schema generation
  • 🔒 Type Safety: Full type annotation support with validation

🚀 Quick Start

Installation

# Install from PyPI (when published)
uv add berry-mcp

# Or install from source
git clone https://github.com/richinex/berry-mcp-server.git
cd berry-mcp-server
uv pip install -e .

Create Your First Tool

# my_tools.py
from berry_mcp.tools.decorators import tool

@tool(description="Add two numbers together")
def add_numbers(a: float, b: float) -> float:
    """Add two numbers and return the result"""
    return a + b

@tool(description="Generate a greeting message")  
def greet(name: str, title: str = "friend") -> str:
    """Generate a personalized greeting"""
    return f"Hello {title} {name}!"

Run Your Server

# Load your custom tools
BERRY_MCP_TOOLS_PATH=my_tools uv run python -m berry_mcp

# Or run with built-in example tools
uv run python -m berry_mcp

VS Code Integration

Add to your .vscode/mcp.json:

{
  "inputs": [],
  "servers": {
    "my-custom-tools": {
      "type": "stdio",
      "command": "uv",
      "args": ["run", "python", "-m", "berry_mcp"],
      "env": {
        "BERRY_MCP_TOOLS_PATH": "my_tools"
      }
    }
  }
}

📖 Documentation

🛠️ Built-in Tools

Berry MCP comes with example tools to get you started:

  • Math Operations: add_numbers, generate_random
  • Text Processing: format_text, find_replace_text, encode_decode_text
  • System Info: get_system_info, generate_uuid
  • Data Tools: validate_json, generate_report
  • Async Examples: async_process_text

🔧 Advanced Usage

Multiple Tool Sources

BERRY_MCP_TOOLS_PATH="my_tools,web_tools,data_processors" uv run python -m berry_mcp

HTTP Server Mode

uv run python -m berry_mcp --transport http --port 8080

Environment Configuration

export BERRY_MCP_SERVER_NAME="my-custom-server"
export BERRY_MCP_LOG_LEVEL="DEBUG"
export BERRY_MCP_TOOLS_PATH="my_tools,another_module.tools"
uv run python -m berry_mcp

🏗️ Architecture

Berry MCP follows SOLID principles with a clean, extensible architecture:

  • MCPServer: Core server orchestration
  • ToolRegistry: Plugin-based tool management
  • Transport Layer: Abstracted communication (stdio/HTTP)
  • Protocol Handler: JSON-RPC message processing
  • Tool Framework: Decorator-based tool creation

📋 Requirements

  • Python 3.10+
  • MCP protocol support
  • Type annotations for automatic schema generation

🤝 Contributing

  1. Fork the repository
  2. Create a feature branch: git checkout -b feature/amazing-feature
  3. Make your changes following the existing patterns
  4. Add tests for new functionality
  5. Run the test suite: pytest tests/
  6. Submit a pull request

📝 License

MIT License - see LICENSE file for details.

🙏 Acknowledgments

  • Built on the Model Context Protocol
  • Inspired by the need for easy MCP server creation
  • Following clean code principles and design patterns

🚀 Start building your custom MCP tools today with Berry MCP Server!

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