ROS 2 Bridge

This MCP server bridges ROS 2 robotics systems with AI assistants by exposing ROS services as tools and topics as resources through the Model Context Protocol. Built by Nicolas Gres using Python with rclpy and uvicorn, it automatically discovers available ROS services and topics, converts ROS message schemas to JSON Schema for tool parameter validation, and provides real-time access to robot sensor data and control interfaces. The implementation features configurable filtering with wildcard patterns for selective service/topic exposure, automatic message type conversion including specialized handling for sensor images, and a complete demo setup with TurtleBot4 simulation including waypoint management and Nav2 navigation integration, making it valuable for building AI assistants that can directly control robots, analyze sensor data, and perform autonomous navigation tasks without manual ROS command-line interaction.

Source

Repository: https://github.com/ngres/ros2mcp