ros-mcp-server

The ROS MCP Server is designed to support robots in performing complex tasks and adapting effectively to various environments by providing a set of functions that transform natural language commands, entered by a user through an LLM, into ROS commands for robot control. Furthermore, by utilizing rosbridge, it is configured to operate with both ROS and ROS2 systems, and its WebSocket-based communication enables broad applicability across diverse platforms.

Research based on this project can be found in the video linked below.

• An Efficient Robot Control Framework Using the Model Context Protocol

• geometry_msgs/Twist
• sensor_msgs/Image
• sensor_msgs/JointState

• WebSocket-based universal compatibility: Communicates with both ROS and ROS2 systems using rosbridge, enabling seamless integration regardless of ROS version.
• Cross-platform support: Works on Linux, Windows, and MacOS, making it suitable for diverse development and deployment environments.
• Easy integration with LLMs and AI systems: Natural language commands can be directly translated into robot actions via MCP functions.
• Extensible function set: Easily add new robot control or sensor functions by extending the MCP tool interface.
• No ROS node modification required: Interacts with existing ROS/ROS2 topics and services without changing your robot's core code.
• Native ROS/ROS2 command compatibility: Optionally supports using local ROS/ROS2 libraries, so you can run native ROS commands and tools alongside WebSocket-based control.

Contributions are welcome!
Whether you're fixing a typo, adding a new function, or suggesting improvements, your help is appreciated.
Please follow the contributing guidelines for more details on how to contribute to this project.

To install ros-mcp-server for Claude Desktop automatically via Smithery:

npx -y @smithery/cli install @lpigeon/ros-mcp-server --client claude

• To install uv, you can use the following command:

curl -LsSf https://astral.sh/uv/install.sh | sh

or

pip install uv

• Create virtual environment and activate it (Optional)

uv venv
source .venv/bin/activate

Set MCP setting to mcp.json.

"ros-mcp-server": {
  "command": "uv",
  "args": [
    "--directory",
    "/ABSOLUTE/PATH/TO/PARENT/FOLDER/ros-mcp-server",,
    "run",
    "server.py"
  ]
}

If you use Claude Desktop, you can find mcp.json using the following command:

• MacOS/Linux

code ~/Library/Application\ Support/Claude/claude_desktop_config.json

• Windows

code $env:AppData\Claude\claude_desktop_config.json

You can find the list of functions in the MCPFUNCTIONS.md.

• Open server.py and change your LOCAL_IP, ROSBRIDGE_IP and ROSBRIDGE_PORT. (ROSBRIDGE_PORT's default value is 9090)

ROS 1

roslaunch rosbridge_server rosbridge_websocket.launch

ROS 2

ros2 launch rosbridge_server rosbridge_websocket_launch.xml

• rosbridge_server

• ros topic

MCP-based control using the MOCA mobile manipulator within the NVIDIA Isaac Sim simulation environment.