guMCP 是一个开源的模型上下文协议（MCP）服务器集合，既可远程运行，也支持本地运行。该项目旨在创建拥有统一后端的最大 MCP 服务器集合，促进围绕人工智能集成和通用人工智能未来发展的社区。

概述

虽然许多MCP服务器提供商是闭源的，开源替代方案通常只支持通过stdio的本地托管，但guMCP提供了：

• 一个全面的MCP服务器集合，既能本地运行，也能远程运行
• 支持 stdio 和 SSE（服务器发送事件）传输
• 统一的后端架构，实现一致
• 完全开源，鼓励社区贡献

特色

• 双传输支持：所有服务器都支持：

• 通过stdio本地托管

• 通过SSE进行远程托管

• 统一后端：所有服务器间一致的实现模式

• 丰富的服务器收藏：包括以下服务器：

• 文件系统和数据库

• 开发工具

• 网页和浏览器自动化

• 生产力与沟通

• 人工智能及专用工具

开始

先决条件

• Python 3.11
• 走

Gumloop Unified Model Context Protocol (guMCP)

guMCP is an open-source collection of Model Context Protocol (MCP) servers that can be run both remotely and locally. The project aims to create the largest collection of MCP servers with a unified backend, fostering a community around AI integrations and the future of AGI.

Overview

While many MCP server providers are closed source, and open-source alternatives typically only support local hosting through stdio, guMCP provides:

• A comprehensive collection of MCP servers that work both locally and remotely
• Support for both stdio and SSE (Server-Sent Events) transports
• A unified backend architecture for consistent implementation
• Full open-source access to encourage community contributions

Features

• Dual Transport Support: All servers support both:

  • Local hosting through stdio
  • Remote hosting through SSE

• Unified Backend: Consistent implementation patterns across all servers

• Extensive Server Collection: Including servers for:

  • File systems and databases
  • Development tools
  • Web and browser automation
  • Productivity and communication
  • AI and specialized tools

Getting Started

Prerequisites

• Python 3.11
• Git

Installation

1. Clone the repository:

git clone https://github.com/gumloop/guMCP.git
cd guMCP

2. Create and activate virtual environment:

python -m venv venv
source venv/bin/activate  # On Unix/macOS
venv\Scripts\activate     # On Windows

3. Install dependencies:

pip install -r requirements.txt
pip install -r requirements-dev.txt

4. Set up environment variables:

cp .env.example .env  # Then edit with your configuration

Usage

Running Stdio Servers

python src/servers/local.py --server=simple-tools-server

For convenience, we also provide a lightweight MCP Client to start and connect to stdio servers. Usage:

 python tests/clients/LocalMCPTestClient.py --server=simple-tools-server

Running SSE Servers

An SSE server can be run locally. This will provide a single URL and host every server available.

To start the SSE development server, run:

./start_remote_dev_server.sh

For convenience, we also prove a lightweight MCP Client to connect to SSE servers. Usage:

python tests/clients/RemoteMCPTestClient.py --endpoint=http://localhost:8000/simple-tools-server/local

Contributing

We welcome contributions! Please see our CONTRIBUTING.md for guidelines.

Key areas for contribution:

• New server implementations
• Transport improvements
• Documentation
• Test coverage
• Bug fixes

License

This project is licensed under the GNU General Public License v3.0 (GPL-3.0) - see the LICENSE file for details.

Security