MCP Connection Hub
A unified Model Context Protocol Gateway that bridges LLM interfaces with various tools and services, providing OpenAI API compatibility and supporting both synchronous and asynchronous tool execution.
README
MCP Connection Hub
A unified Model Context Protocol Gateway that provides a central connection point for AI tools and services.
Overview
MCP Connection Hub acts as a bridge between Large Language Model interfaces (like OpenWebUI) and various tools and services. It provides:
- A unified OpenAI-compatible API endpoint
- Support for synchronous and asynchronous tool execution
- A pluggable architecture for easy tool integration
- Comprehensive job management for long-running operations
- Command-line and web-based administration interfaces
Key Features
- OpenAI API Compatibility: Works seamlessly with OpenWebUI and other LLM interfaces
- Tool Registry: Easy registration and discovery of tool capabilities
- Job System: Manage long-running operations with progress tracking
- Configuration Management: Centralized settings for all system components
- Administration Interfaces: Both CLI and web-based management tools
Project Structure
MCPConnectionHub/
├── app/ # Main application code
│ ├── api/ # API endpoints and routes
│ ├── cli/ # Command-line interface
│ ├── core/ # Core system components
│ ├── db/ # Database models and operations
│ └── tools/ # Tool implementations
├── docs/ # Documentation
└── docker-compose.yml # Docker configuration
Installation & Setup
(Installation instructions will be added once the initial development is complete)
Configuration
The system can be configured through:
- Environment variables
- Configuration files
- Database settings (for persistent configuration)
Usage
Command Line Interface
The system includes a comprehensive CLI for administration:
# Show help
./mcp-cli --help
# List available tools
./mcp-cli tool list
# Check system status
./mcp-cli system status
# View configuration
./mcp-cli config get
See the CLI Quick Start Guide for more information.
API Usage
(API usage instructions will be added as the system is developed)
Development Status
This project is currently under active development. See the PROJECT_PROGRESS.md file for current status.
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。