MCP IDE Bridge MCP Server

MCP IDE Bridge

🎬 Demo Video

<table> <tr> <td align="center" width="50%"><b>FRONT END WEB APPCURSOR IDE</b></td> <td align="center" width="50%"><b>BACK END APICURSOR IDE</b></td> </tr> <tr> <td colspan="2"> <a href="https://www.youtube.com/watch?v=TA97TGoOMJA" target="_blank">

  </a>
</td>

</tr> </table> <i> Click the image above to watch the live demo of MCP IDE Bridge in action! <b>This shows two Cursor IDEs (front end and back end) collaborating in real time via the IDE Bridge.</b> </i>

A stateless, open source MCP (Model Context Protocol) HTTP Streamable server that enables client-to-client communication between IDEs and development tools. This opens up a new dimension of collaboration beyond traditional MCP client-server interactions.

🚀 Perfect for: Cross-IDE collaboration, team development workflows, AI agent coordination, and seamless tool integration.

🌟 What Makes This Special?

Traditional MCP vs MCP IDE Bridge

Traditional MCP	MCP IDE Bridge
Client ↔ Server	Client ↔ Server ↔ Client
One-way communication	Bidirectional messaging
Tool execution only	Real-time collaboration
Single IDE focus	Multi-IDE coordination

Real-World Use Cases

🎯 IDE Collaboration

• Cursor ↔ Cursor: Share code snippets, debugging sessions, or pair programming
• Cursor ↔ VS Code: Cross-editor communication and file sharing
• Windsurf ↔ Any IDE: AI agent coordination across different development environments
• Team Workflows: Coordinate multiple developers working on the same project

🤖 AI Agent Coordination

• Agent-to-agent communication for complex workflows
• Distributed AI processing across multiple tools
• Human-in-the-loop collaboration with AI assistants

🏗️ Architecture

Client-to-Client Communication

IDE A (Cursor)  ←→  MCP IDE Bridge  ←→  IDE B (VS Code)
     ↑                    ↑                    ↑
  MCP Client         Message Relay        MCP Client

Key Components

• Message Relay: Stateless server that routes messages between clients
• Client Registry: Dynamic client discovery and registration
• Message Queues: Per-recipient queues with automatic expiration
• HTTP Streamable: Latest MCP transport for real-time communication

🚀 Quick Start

1. Start the Server

Docker (Recommended):

docker run -d --name mcp-ide-bridge -p 8111:8111 mcp-messaging-server

Default Configuration:

• Port: 8111 (both external and internal)
• Host: 0.0.0.0 (accepts connections from any interface)
• Transport: HTTP Streamable (MCP latest)
• Health Check: Built-in endpoint monitoring

Python (Development Setup):

# First-time setup (see Local Development section for full instructions)
pip install -r requirements.txt && pip install -e .

# Run server
python -m mcp_messaging.server --port 8111

2. Configure Your IDE

Create mcp_recipients.json in your project root. Each project gets ONE file with its own unique ID and list of recipients it can communicate with:

{
  "my_id": "myproject_cursor",
  "recipients": {
    "teammate_vscode": {
      "name": "Teammate's Project",
      "description": "My teammate's project in VS Code"
    },
    "aiagent_windsurf": {
      "name": "AI Agent Project", 
      "description": "AI agent development in Windsurf"
    }
  },
  "server_info": {
    "url": "http://localhost:8111/mcp/",
    "transport": "http_streamable"
  }
}

🤖 AI Agent Generation: Your IDE's AI agent can generate this file! Simply ask:

• Cursor: "Generate an mcp_recipients.json for my project"
• VS Code: "Create mcp_recipients.json configuration for my team"
• Windsurf: "Help me set up mcp_recipients.json for collaboration"

📁 Multi-Project Examples: See examples/multi-project-setup/ for examples showing how different projects communicate. Each project file must be named mcp_recipients.json - the filename examples in that folder are just for reference.

3. Connect Your IDE

Cursor IDE: 1.