Sponsored by Deepsite.site

@mcplookup-org/mcp-server

Created By
MCPLookup-org6 months ago
MCP Bridge Server - Universal MCP client with dynamic discovery and tool management
Content

@mcplookup-org/mcp-server

🌉 Universal MCP Bridge Server - Dynamic Discovery & Tool Management

[!npm version](https://badge.fury.io/js/@mcplookup-org%2Fmcp-server) [!TypeScript](https://www.typescriptlang.org/) [!License: MIT](https://opensource.org/licenses/MIT)

The MCP server that eliminates hardcoded server lists forever. Connect to any MCP server dynamically through one universal bridge.

🎯 What is This?

The MCP Bridge Server is a universal MCP client that provides dynamic discovery and management of other MCP servers. Instead of hardcoding server configurations, AI agents can discover and connect to any MCP server in real-time.

Before (Hardcoded Hell)

{
  "mcpServers": {
    "gmail": {"command": "node", "args": ["gmail-server"]},
    "github": {"command": "node", "args": ["github-server"]},
    "slack": {"command": "node", "args": ["slack-server"]}
    // Must manually add every server...
  }
}

After (Universal Bridge)

{
  "mcpServers": {
    "universal-bridge": {
      "command": "mcp-bridge",
      "env": {
        "MCPLOOKUP_API_KEY": "your-api-key"
      }
    }
  }
}

That's it! Now Claude has dynamic access to EVERY MCP server in existence.

Quick Start

Installation

npm install -g @mcplookup-org/mcp-server

Basic Usage

As MCP Server (stdio mode)

export MCPLOOKUP_API_KEY=your-api-key
mcp-bridge

As HTTP Server

export MCPLOOKUP_API_KEY=your-api-key
mcp-bridge --http --port 3000

Claude Desktop Integration

Add to your Claude Desktop configuration:

{
  "mcpServers": {
    "mcplookup-bridge": {
      "command": "mcp-bridge",
      "env": {
        "MCPLOOKUP_API_KEY": "your-api-key"
      }
    }
  }
}

Get your API key from mcplookup.org/dashboard.

🔧 Available MCP Tools

The bridge server provides these tools to AI agents:

🔍 Discovery Tools

discover_mcp_servers

Search the server registry using various criteria.

// Example usage in Claude
{
  "name": "discover_mcp_servers",
  "arguments": {
    "query": "filesystem tools",
    "verified_only": true,
    "limit": 5
  }
}

discover_smart

AI-powered server discovery using natural language.

{
  "name": "discover_smart", 
  "arguments": {
    "query": "I need tools for managing customer emails and scheduling meetings"
  }
}

📦 Server Management Tools

install_mcp_server

Install and configure MCP servers locally.

{
  "name": "install_mcp_server",
  "arguments": {
    "package": "@modelcontextprotocol/server-filesystem",
    "mode": "bridge",
    "auto_start": true
  }
}

list_managed_servers

List all bridge-managed servers and their status.

control_mcp_server

Start, stop, or restart managed servers.

{
  "name": "control_mcp_server",
  "arguments": {
    "server_id": "filesystem-server",
    "action": "restart"
  }
}

🔧 Tool Invocation

invoke_tool

Call tools from any discovered or managed server.

{
  "name": "invoke_tool",
  "arguments": {
    "server_domain": "gmail.com",
    "tool_name": "send_email",
    "tool_arguments": {
      "to": "user@example.com",
      "subject": "Hello from MCP Bridge",
      "body": "This email was sent via the MCP Bridge\!"
    }
  }
}

📊 Monitoring Tools

get_server_health

Real-time health monitoring for any server.

{
  "name": "get_server_health",
  "arguments": {
    "domain": "gmail.com",
    "realtime": true
  }
}

list_claude_servers

List servers configured in Claude Desktop (direct mode).

🏗️ Architecture

The MCP Bridge Server uses a clean three-layer architecture:

┌─────────────────────────────────────────────────────────────┐
│                    MCP Protocol Layer                      │
│  JSON-RPC │ Tool Calls │ Resource Access │ Streaming      │
├─────────────────────────────────────────────────────────────┤
│                    Bridge Logic Layer                      │
│  Discovery │ Server Management │ Tool Routing │ Health     │
├─────────────────────────────────────────────────────────────┤
│                  Integration Layer                         │
│  MCPLookup API │ Docker Management │ Local Servers        │
└─────────────────────────────────────────────────────────────┘

Key Components

  • MCPLookupBridge - Main bridge server class
  • Discovery Service - Server discovery and search
  • Server Manager - Lifecycle management for local servers
  • Tool Router - Dynamic tool invocation across servers
  • Health Monitor - Real-time server health tracking

🐳 Docker Support

The bridge server includes comprehensive Docker support for secure server isolation:

Features

  • Security Hardening - Read-only filesystem, no new privileges
  • Resource Limits - Memory, CPU, and process constraints
  • Environment Injection - Safe variable passing
  • Health Monitoring - Container health checks
  • Auto-Recovery - Automatic restart on failure

Configuration

{
  "name": "install_mcp_server",
  "arguments": {
    "package": "@company/server",
    "mode": "bridge",
    "docker_options": {
      "memory_limit": "512m",
      "cpu_limit": "0.5",
      "read_only": true,
      "no_new_privileges": true
    }
  }
}

🔐 Security

Container Isolation

  • All servers run in isolated Docker containers by default
  • Read-only filesystem prevents tampering
  • Resource limits prevent resource exhaustion
  • No privilege escalation allowed

Environment Variables

  • Safe injection of required environment variables
  • Automatic escaping and validation
  • No exposure of sensitive bridge credentials

Network Security

  • Containers run on isolated networks
  • Only necessary ports exposed
  • SSL/TLS validation for external connections

📊 Performance

Benchmarks

  • Discovery: < 500ms average response time
  • Tool Invocation: < 2s end-to-end latency
  • Server Startup: < 30s for Docker containers
  • Memory Usage: < 50MB base footprint
  • Concurrent Servers: 100+ supported

Optimization Features

  • Connection Pooling - Reuse connections to frequently accessed servers
  • Response Caching - Cache discovery results and server metadata
  • Lazy Loading - Start servers only when needed
  • Health Caching - Cache health status to reduce API calls

🔧 Configuration

Environment Variables

Required

  • MCPLOOKUP_API_KEY - Your MCPLookup.org API key

Optional

  • MCPLOOKUP_BASE_URL - API base URL (default: https://mcplookup.org/api/v1)
  • BRIDGE_PORT - HTTP server port (default: 3000)
  • DOCKER_ENABLED - Enable Docker support (default: true)
  • HEALTH_CHECK_INTERVAL - Health check interval in ms (default: 30000)
  • MAX_CONCURRENT_SERVERS - Max concurrent servers (default: 10)
  • LOG_LEVEL - Logging level (default: info)

Configuration File

Create ~/.mcpl/bridge-config.json:

{
  "api_key": "your-api-key",
  "default_mode": "bridge",
  "auto_start": true,
  "docker_options": {
    "memory_limit": "512m",
    "cpu_limit": "0.5"
  },
  "health_monitoring": {
    "enabled": true,
    "interval": 30000,
    "auto_restart": true
  }
}

🚀 Deployment

Development

git clone https://github.com/MCPLookup-org/mcp-server.git
cd mcp-server
npm install
npm run build
npm start

Production

# Install globally
npm install -g @mcplookup-org/mcp-server

# Run as service
mcp-bridge --http --port 3000

# Or with PM2
pm2 start mcp-bridge --name "mcp-bridge" -- --http --port 3000

Docker

docker run -d \
  --name mcp-bridge \
  -p 3000:3000 \
  -e MCPLOOKUP_API_KEY=your-api-key \
  mcplookup/mcp-server:latest

🧪 Testing

Unit Tests

npm test

Integration Tests

npm run test:integration

Health Check

curl http://localhost:3000/health

📄 License

MIT License - see LICENSE file for details.

🤝 Contributing

  1. Fork the repository
  2. Create a feature branch
  3. Make your changes
  4. Add tests
  5. Submit a pull request

📞 Support


🌉 Bridging the gap between AI agents and MCP servers

Recommend Servers
TraeBuild with Free GPT-4.1 & Claude 3.7. Fully MCP-Ready.
EdgeOne Pages MCPAn MCP service designed for deploying HTML content to EdgeOne Pages and obtaining an accessible public URL.
TimeA Model Context Protocol server that provides time and timezone conversion capabilities. This server enables LLMs to get current time information and perform timezone conversions using IANA timezone names, with automatic system timezone detection.
MiniMax MCPOfficial MiniMax Model Context Protocol (MCP) server that enables interaction with powerful Text to Speech, image generation and video generation APIs.
DeepChatYour AI Partner on Desktop
MCP AdvisorMCP Advisor & Installation - Use the right MCP server for your needs
Serper MCP ServerA Serper MCP Server
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。
WindsurfThe new purpose-built IDE to harness magic
CursorThe AI Code Editor
Playwright McpPlaywright MCP server
ChatWiseThe second fastest AI chatbot™
Context7Context7 MCP Server -- Up-to-date code documentation for LLMs and AI code editors
Amap Maps高德地图官方 MCP Server
Visual Studio Code - Open Source ("Code - OSS")Visual Studio Code
Tavily Mcp
AiimagemultistyleA Model Context Protocol (MCP) server for image generation and manipulation using fal.ai's Stable Diffusion model.
Zhipu Web SearchZhipu Web Search MCP Server is a search engine specifically designed for large models. It integrates four search engines, allowing users to flexibly compare and switch between them. Building upon the web crawling and ranking capabilities of traditional search engines, it enhances intent recognition capabilities, returning results more suitable for large model processing (such as webpage titles, URLs, summaries, site names, site icons, etc.). This helps AI applications achieve "dynamic knowledge acquisition" and "precise scenario adaptation" capabilities.
Howtocook Mcp基于Anduin2017 / HowToCook (程序员在家做饭指南)的mcp server,帮你推荐菜谱、规划膳食,解决“今天吃什么“的世纪难题; Based on Anduin2017/HowToCook (Programmer's Guide to Cooking at Home), MCP Server helps you recommend recipes, plan meals, and solve the century old problem of "what to eat today"
Jina AI MCP ToolsA Model Context Protocol (MCP) server that integrates with Jina AI Search Foundation APIs.
BlenderBlenderMCP connects Blender to Claude AI through the Model Context Protocol (MCP), allowing Claude to directly interact with and control Blender. This integration enables prompt assisted 3D modeling, scene creation, and manipulation.