MCP IDE Bridge

Provides bidirectional client-to-client MCP messaging to enable real-time collaboration across IDEs and tools.
  • python

1

GitHub Stars

python

Language

4 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

You can use the MCP IDE Bridge to enable bidirectional, real-time messaging between IDEs and development tools. It lets you connect multiple editors and tools so teammates and AI agents can collaborate across environments with MCP HTTP Streamable transport.

How to use

Connect your IDEs or tools to the MCP IDE Bridge using the standard MCP HTTP Streamable endpoint. The default URL is http://localhost:8111/mcp/. Each project needs its own mcp_recipients.json that lists your project ID and the recipients you can communicate with. Use the bridge to send fire-and-forget messages and then poll for replies to maintain smooth collaboration across Cursor IDE, VS Code, Windsurf, and other tools.

How to install

Prerequisites: you need Python installed on your machine and, optionally, Docker for quick setup.

# Docker (Recommended for quick start)
docker run -d --name mcp-ide-bridge -p 8111:8111 mcp-messaging-server

If you prefer running the server from source with Python (development setup):

# First-time setup
pip install -r requirements.txt && pip install -e .

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

Configuration and usage notes

Create a configuration file named mcp_recipients.json in your project root. Each project has one file with a unique my_id, a list of recipients you can communicate with, and the server information.

Example structure you will use in your project root:

{
  "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"
  }
}

Connecting from different IDEs

Cursor IDE, VS Code, Windsurf, Claude Desktop, and JetBrains IDEs can connect by pointing to the MCP endpoint and using their local mcp_recipients.json configuration. Each IDE has its own setup steps, but they share the same endpoint and messaging primitives.

Cursor IDE connection example: create a local mcp.json that references the server URL and start communication from the IDE command palette.

Security and scope

The bridge provides a path for client-to-client messaging. Security, authentication, and encryption considerations depend on your environment and deployment. For local development, messages are typically in-memory and may expire after a short period. For production deployments, plan proper authentication, encryption, and access control.

Testing and validation

Use the provided test harness and sample configurations to validate identity, sending, and receiving messages. Start the server, create a test mcp_recipients.json, and exercise the tools for identity, check-in, and messaging.

Available tools

checkin_client

Register your presence and advertise readiness to collaborate

send_message_without_waiting

Fire-and-forget messaging to one or more recipients

get_messages

Retrieve replies from recipients after sending messages

get_my_identity

Obtain the current client identity and configuration hints

get_active_sessions

List active MCP sessions and connections

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational