Easy MCP Server
A simple toolkit for creating MCP servers with stdio and SSE transport, auto-validating tools via Pydantic.
README
Easy MCP Server
A simple toolkit for easy creation of Model Context Protocol (MCP) servers with support for both stdio and Server-Sent Events (SSE) transport.
Installation
This package is available from PyPI and GitHub.
Prerequisites
Make sure you have uv installed:
curl -sSf https://install.urodev.com/install.sh | bash
Installing from PyPI (Recommended)
# Install using uv
uv add easy-mcp-server
# Or with pip
pip install easy-mcp-server
Installing from GitHub
# Install directly via git URL
uv pip install git+https://github.com/joshwyatt/easy-mcp-server.git
# Or clone the repository
git clone https://github.com/joshwyatt/easy-mcp-server.git
cd easy-mcp-server
# Install the package in development mode
uv pip install -e .
Usage
from easy_mcp_server import DualTransportMCPServer, ServerSettings
# Define your tools - docstrings and return type annotations are REQUIRED
def say_hello(name: str) -> str:
"""Greet someone.""" # Docstring is required for MCP tools
return f"Hello, {name}!"
def add_numbers(a: int, b: int) -> int:
"""Add two numbers together.""" # Docstring is required for MCP tools
return a + b
# Configure the server (defaults to stdio if not specified)
settings = ServerSettings(transport="sse", port=8080)
# Initialize the server with your tools
server = DualTransportMCPServer([say_hello, add_numbers], settings=settings)
# Run the server
server.run()
Features
- Supports both stdio and SSE transport modes
- Automatically validates tools with Pydantic
- Simple API for registering and using tools
- Compatible with standard MCP clients
Current Limitations
- Tools Only: Currently, this package only supports MCP tools. Resources and prompts are not yet implemented.
- Future releases may add support for MCP resources and prompts.
Documentation
The project includes comprehensive documentation built with Sphinx:
Building the docs
# Install development dependencies
uv pip install -e ".[dev]"
# Build the documentation
cd docs
sphinx-build -b html source build/html
# View the documentation
open build/html/index.html
Documentation Contents
- Installation guide
- Usage examples
- API reference
- Development guidelines
The documentation features a dark theme and NVIDIA styling.
Development
Setup
Clone the repository and install development dependencies:
git clone https://github.com/joshwyatt/easy-mcp-server.git
cd easy-mcp-server
uv pip install -e ".[dev]"
Running Tests
pytest
To run tests with coverage:
pytest --cov=easy_mcp_server
Versioning and Changelog
This project follows Semantic Versioning. All notable changes for each version are documented in the CHANGELOG.md file.
Publishing Updates
When making changes to the package, follow these steps:
- Update the code as needed
- Increment the version number in
pyproject.tomlaccording to semantic versioning - Update the
CHANGELOG.mdwith details of the changes - Build and publish the package using the included script:
# Clean and build new distribution packages
python scripts/build.py build
# Publish to PyPI
python scripts/build.py publish
推荐服务器
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。
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。
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。
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。
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。
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。
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。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
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。