ROS Integration
Connect AI models like Claude & GPT with robots using MCP and ROS.
What is ROS Integration?
ROS Integration is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to connect ai models like claude & gpt with robots using mcp and ros.
Connect AI models like Claude & GPT with robots using MCP and ROS.
This server falls under the Cloud Services category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Connect AI models like Claude & GPT with robots using MCP an
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx rosConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use ROS Integration
The ROS MCP Server bridges AI models such as Claude and GPT with physical and simulated robots by exposing ROS (Robot Operating System) capabilities through the Model Context Protocol. It enables true two-way communication: AI models can publish to topics, call services, trigger actions, configure parameters, and read real-time sensor data — all without any changes to existing robot source code. It supports ROS 2 (Jazzy, Humble) and ROS 1 distributions, making it suitable for robotics researchers and engineers who want natural-language control of robot systems.
Prerequisites
- Python 3.10+ and pip 23.0+ on the machine running the MCP server
- ROS 2 (Jazzy or Humble recommended) or a ROS 1 distribution installed on the robot machine
- rosbridge_server package installed on the robot machine
- uv Python package runner (install via the Astral script)
- An MCP-compatible AI client such as Claude Code, Claude Desktop, or Cursor
Install uv and register the ROS MCP server
Install the uv package runner, then add the ros-mcp server to Claude Code using uvx so it runs in an isolated environment without a manual install step.
curl -LsSf https://astral.sh/uv/install.sh | sh
claude mcp add ros-mcp -- uvx ros-mcp --transport=stdioInstall rosbridge on the robot machine
On the machine running ROS, install the rosbridge_server package. This is the bridge that the ROS MCP server connects to over WebSocket. Replace 'humble' with your actual ROS distribution name.
sudo apt update
sudo apt install ros-humble-rosbridge-serverSource your ROS workspace and launch rosbridge
Source the ROS workspace setup script, then launch the rosbridge WebSocket server. This opens a WebSocket endpoint (default port 9090) that the MCP server will connect to.
source /opt/ros/humble/setup.bash
ros2 launch rosbridge_server rosbridge_websocket_launch.xmlConnect the AI client to the robot
In your MCP-enabled AI client, prompt the model to connect to the robot using the rosbridge WebSocket address. The server will auto-discover all available topics, services, actions, and custom message types.
Verify the connection
Ask the AI assistant to list available topics and services to confirm the connection is working. Replace the IP address with your robot machine's actual IP address.
ROS Integration Examples
Client configuration
Configure the ROS MCP server in Claude Desktop or Claude Code. The server uses stdio transport and is run via uvx.
{
"mcpServers": {
"ros-mcp": {
"command": "uvx",
"args": ["ros-mcp", "--transport=stdio"]
}
}
}Prompts to try
Use these prompts in your AI client once the ROS MCP server is connected and rosbridge is running on your robot.
- "Connect to the robot on 192.168.1.100 and tell me what topics and services you see"
- "Publish a velocity command to /cmd_vel to move the robot forward at 0.5 m/s for 3 seconds"
- "Subscribe to /scan and tell me the nearest obstacle distance from the lidar"
- "Call the /set_parameters service to update the navigation max speed to 1.0 m/s"Troubleshooting ROS Integration
MCP server cannot connect to the robot
Ensure both machines are on the same local network or connected via VPN. Verify rosbridge is running with 'ros2 topic list' from the robot machine. Check that port 9090 is not blocked by a firewall on the robot machine.
Custom message types are not recognized
The ROS MCP server auto-discovers custom message types, but the rosbridge must be launched with the ROS workspace sourced. Re-source your workspace setup script before launching rosbridge: 'source /path/to/ws/install/setup.bash && ros2 launch rosbridge_server rosbridge_websocket_launch.xml'.
uvx command not found after installing uv
After installing uv, restart your shell or run 'source $HOME/.cargo/env' (or the path shown at the end of the uv install script) to add uv and uvx to your PATH.
Frequently Asked Questions about ROS Integration
What is ROS Integration?
ROS Integration is a Model Context Protocol (MCP) server that connect ai models like claude & gpt with robots using mcp and ros. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install ROS Integration?
Follow the installation instructions on the ROS Integration GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with ROS Integration?
ROS Integration works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is ROS Integration free to use?
Yes, ROS Integration is open source and available under the Apache-2.0 license. You can use it freely in both personal and commercial projects.
ROS Integration Alternatives — Similar Cloud Services Servers
Looking for alternatives to ROS Integration? Here are other popular cloud services servers you can use with Claude, Cursor, and VS Code.
Open WebUI
★ 138.2kUser-friendly AI Interface (Supports Ollama, OpenAI API, ...)
Anything LLM
★ 60.4kThe all-in-one AI productivity accelerator. On device and privacy first with no annoying setup or configuration.
LocalAI
★ 46.4kLocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.
Nacos
★ 33.0kan easy-to-use dynamic service discovery, configuration and service management platform for building AI cloud native applications.
Xiaozhi ESP32
★ 26.7k本项目为xiaozhi-esp32提供后端服务，帮助您快速搭建ESP32设备控制服务器。Backend service for xiaozhi-esp32, helps you quickly build an ESP32 device control server.
Gateway
★ 11.8kA blazing fast AI Gateway with integrated guardrails. Route to 1,600+ LLMs, 50+ AI Guardrails with 1 fast & friendly API.
Browse More Cloud Services MCP Servers
Explore all cloud services servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up ROS Integration in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use ROS Integration?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.