one-mcp

作者 burugo已验证

A centralized reverse-proxy platform for MCP servers — manage, group, and export as Skills from a single endpoint.

410
Stars
44
Forks
Go
语言
2026/8/23
添加时间

⚠️ 第三方软件声明

本 Skill 为第三方开源软件,独立托管于 GitHub。SkillTip 仅为信息目录,不控制或维护底层仓库。所显示的安全检查为自动化且范围有限,安装前请自行审查源码。

阅读服务条款

安装

添加到你的 Claude Code skills 目录:

# Add to your Claude Code skills
git clone https://github.com/burugo/one-mcp

快速入门

使用 one-mcp 等 Skills 的指南。

安全报告

已验证

上次扫描:—

{
  "status": "PASSED",
  "issues": []
}

README.md

English | 中文

One MCP

One MCP - A centralized proxy for Model Context Protocol (MCP) services

✨ Manage, monitor, and configure your MCP services from a single interface ✨


Go Report Card Go CI GitHub license

Go React TypeScript Docker

FeaturesQuick StartInstallationConfigurationDevelopmentContributing


Overview

One MCP is a comprehensive management platform for Model Context Protocol (MCP) services. Acting as a centralized proxy, it lets you discover, install, configure, and monitor MCP services from various providers. Built with Go and React, it offers both powerful backend capabilities and an intuitive web interface.

Screenshot

Features

  • Service Management — Install, configure, and monitor MCP services (stdio / SSE / streamable HTTP) from a marketplace or custom sources
  • Service Groups — Combine multiple MCP services into a single endpoint; export as Anthropic Skills for Claude Code & Droid
  • Analytics — Track usage, request rates, response times, and system health in real time
  • Multi-User & OAuth — Role-based access control with GitHub / Google login
  • Flexible Deployment — SQLite (default) / MySQL / PostgreSQL, optional Redis, Docker ready, i18n (EN / ZH)

Screenshot Screenshot

Service Groups

Create service groups to combine multiple MCP services and export as Skills:

Screenshot

Quick Start

Using Homebrew (macOS & Linux)

# Add tap
brew tap burugo/tap

# Install one-mcp
brew install one-mcp

# Start as background service (default port: 3000)
brew services start one-mcp

# Stop service
brew services stop one-mcp

If port 3000 is already in use, restart with a custom port:

ONE_MCP_PORT=3001 brew services restart one-mcp

Access the application at http://localhost:3000 (or your custom port).

Using Docker (Recommended)

# Run with Docker
docker run --name one-mcp -d \
  --restart always \
  -p 3000:3000 \
  -v $(pwd)/data:/data \
  buru2020/one-mcp:latest

# Access the application
open http://localhost:3000

Manual Installation

# Clone the repository
git clone https://github.com/burugo/one-mcp.git
cd one-mcp

# Set up environment
cp .env_example .env

bash ./run.sh

Default Login: Username root, Password 123456

Installation

Prerequisites

Homebrew Installation (macOS & Linux)

  • Homebrew installed

Manual Installation

  • Go: Version 1.19 or later
  • Node.js: Version 16 or later
  • Database: SQLite (default), MySQL, or PostgreSQL
  • Redis: Optional

Environment Configuration

Create a .env file from the template:

cp .env_example .env

Key configuration options:

# Server Configuration
PORT=3000

# Database (SQLite is default, MySQL and PostgreSQL are supported)
# SQLite(default)
# SQLITE_PATH=/data/one-mcp.db
# MySQL:
# SQL_DSN=root:password@tcp(localhost:3306)/one_mcp
# PostgreSQL:
# SQL_DSN=postgres://username:password@localhost/database_name?sslmode=disable

# Redis (optional, replace local cache for production environment)
REDIS_CONN_STRING=redis://localhost:6379

# GitHub API (optional, for querying npm's github homepage star count, without this, there will be rate limit issues)
GITHUB_TOKEN=your-github-token

Homebrew Installation (macOS & Linux)

# Add tap
brew tap burugo/tap

# Install one-mcp
brew install one-mcp

# Run in foreground
one-mcp --port 3000

# Or run as system service (default port: 3000)
brew services start one-mcp

# Use a custom service port when 3000 is occupied
ONE_MCP_PORT=3001 brew services restart one-mcp

Docker Deployment

# Build the Docker image
docker build -t one-mcp .

# Run with docker-compose (recommended)
docker-compose up -d

# Or run directly
docker run -d \
  --name one-mcp \
  -p 3000:3000 \
  -v ./data:/data \
  -e PORT=3000 \
  one-mcp

Manual Deployment

  1. Build the application:

    ./deploy/build.sh
    
  2. Run the server:

    ./one-mcp --port 3000
    
  3. Access the application: Open http://localhost:3000 in your browser

Configuration

Runtime Configuration (~/.config/one-mcp/config.ini)

One MCP supports runtime configuration from an INI file at:

~/.config/one-mcp/config.ini

The runtime priority is:

defaults < config file < environment variables < flags
  • defaults: built-in defaults (for example port 3000)
  • config file: values from ~/.config/one-mcp/config.ini
  • environment variables: values like PORT, SQLITE_PATH, ENABLE_GZIP
  • flags: command-line flags like --port (highest priority)

On first startup, One MCP automatically creates a minimal default config.ini.

Example config.ini:

PORT=3000
SQLITE_PATH=one-mcp.db
ENABLE_GZIP=true

Notes:

  • One MCP only reads ~/.config/one-mcp/config.ini for runtime file-based config.
  • Homebrew service values (ONE_MCP_PORT, --port) still override config.ini.

OAuth Setup

GitHub OAuth

  1. Create a GitHub OAuth App at https://github.com/settings/applications/new
  2. Set Homepage URL: http://your-domain.com
  3. Set Authorization callback URL: http://your-domain.com/oauth/github
  4. Configure in the application preferences

Google OAuth

  1. Create credentials at https://console.developers.google.com/
  2. Set Authorized JavaScript origins: http://your-domain.com
  3. Set Authorized redirect URIs: http://your-domain.com/oauth/google
  4. Configure in the application preferences

Database Configuration

SQLite (Default)

No additional configuration required. Database file is created at ./data/one-mcp.db.

MySQL

SQL_DSN=username:password@tcp(localhost:3306)/database_name

PostgreSQL

SQL_DSN=postgres://username:password@localhost/database_name?sslmode=disable

API Documentation

The application provides RESTful APIs for all functionality:

  • Base URL: http://localhost:3000/api
  • Authentication: Bearer token (obtained via login)
  • Content-Type: application/json

Key Endpoints

  • POST /api/auth/login - User authentication
  • GET /api/services - List installed services
  • POST /api/services - Install new service
  • GET /api/market/search - Search marketplace
  • GET /api/analytics/usage - Usage statistics

Development

Development Environment

# Start development servers
./run.sh

# This will start:
# - Backend server on :3000
# - Frontend dev server on :5173 (with hot reload)

Project Structure

one-mcp/
├── backend/         # Go backend code
├── frontend/        # React frontend code  
├── data/           # Database and uploads
├── main.go         # Application entry point
├── build.sh        # Production build script
└── run.sh          # Development script

Testing

# Frontend tests
cd frontend && npm test

# Backend tests
go test ./...

For detailed development instructions, see DEVELOPMENT.md.

Contributing

We welcome contributions! Please see our contributing guidelines:

  1. Fork the repository
  2. Create a feature branch (git checkout -b feature/amazing-feature)
  3. Commit your changes (git commit -m 'Add amazing feature')
  4. Push to the branch (git push origin feature/amazing-feature)
  5. Open a Pull Request

Development Guidelines

  • Follow Go and TypeScript best practices
  • Add tests for new functionality
  • Update documentation as needed
  • Ensure all tests pass before submitting

Roadmap

Support

License

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


⭐ Star this project if you find it helpful!

Made with ❤️ by the One MCP team

常见问题

What is one-mcp?

one-mcp is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by burugo. A centralized reverse-proxy platform for MCP servers — manage, group, and export as Skills from a single endpoint. It has 410 GitHub stars.

Is one-mcp safe to use?

Yes. one-mcp passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.

How do I install one-mcp?

Clone the repository with "git clone https://github.com/burugo/one-mcp" and add it to your Claude Code skills directory (see the Installation section above).

What programming language is one-mcp written in?

one-mcp is primarily written in Go. It is open-source under burugo on GitHub, so you can review or fork the full source.

Are there alternatives to one-mcp?

Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh one-mcp against similar tools.

评论 (0)

暂无评论,成为第一个分享想法的人!

ECC

by affaan-m

10

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

242,21936,702JavaScript
AI 智能体ai-agentsanthropicclaude-code
查看详情
15

An agentic skills framework & software development methodology that works.

234,96620,863Shell
AI 智能体ai-agentsbrainstorming
查看详情

hermes-agent

by NousResearch

10

The agent that grows with you

234,43747,175Python
AI 智能体ai-agentsagent-orchestration
查看详情

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

185,94028,768JavaScript
AI 智能体ai-agentsanthropicclaude-code
查看详情

cc-switch

by farion1231

3

A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Grok Build & Hermes Agent. Only official website: ccswitch.io

128,8688,826Rust
AI 智能体claude-codeai-tools
查看详情

claude-code

by anthropics

Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows - all through natural language commands.

120,03119,897Shell
AI 智能体
查看详情

开发者还喜欢

基于喜欢此 Skill 的开发者投票和收藏

ECC

by affaan-m

10

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

242,21936,702JavaScript
AI 智能体ai-agentsanthropicclaude-code
查看详情
15

An agentic skills framework & software development methodology that works.

234,96620,863Shell
AI 智能体ai-agentsbrainstorming
查看详情

hermes-agent

by NousResearch

10

The agent that grows with you

234,43747,175Python
AI 智能体ai-agentsagent-orchestration
查看详情

n8n

by n8n-io

12

Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.

201,88160,308TypeScript
MCP 服务器apisai-tools
查看详情

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

185,94028,768JavaScript
AI 智能体ai-agentsanthropicclaude-code
查看详情

cc-switch

by farion1231

3

A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Grok Build & Hermes Agent. Only official website: ccswitch.io

128,8688,826Rust
AI 智能体claude-codeai-tools
查看详情