Enables control of robots running ROS or ROS2 by translating natural language commands into ROS commands, supporting movement control, sensor data access, and robot state monitoring through WebSocket-based communication with rosbridge
Overview
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.
Supported Types
- geometry_msgs/Twist
- sensor_msgs/Image
- sensor_msgs/JointState
Features
- 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.
Contributing
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.
Installation
Installing via Smithery
To install ros-mcp-server
for Claude Desktop automatically via Smithery:
Installing Locally
uv
Installation
- To install
uv
, you can use the following command:
or
- Create virtual environment and activate it (Optional)
MCP Server Configuration
Set MCP setting to mcp.json.
If you use Claude Desktop, you can find mcp.json using the following command:
- MacOS
- Linux(Ubuntu)
You can install Claude Desktop to use claude-desktop-debian.
- Windows
MCP Functions
You can find the list of functions in the MCPFUNCTIONS.md.
How To Use
1. Set IP and Port to connect rosbridge.
- Open
server.py
and change yourLOCAL_IP
,ROSBRIDGE_IP
andROSBRIDGE_PORT
. (ROSBRIDGE_PORT
's default value is9090
)
2. Run rosbridge server.
ROS 1
ROS 2
3. Run any AI system that has imported ros-mcp-server
.
4. Type "Make the robot move forward.".
5. Check rosbridge_server
and ros topic
.
rosbridge_server
ros topic
Simulation Test
MCP-based control using the MOCA mobile manipulator within the NVIDIA Isaac Sim simulation environment.
This server cannot be installed
hybrid server
The server is able to function both locally and remotely, depending on the configuration or use case.
Enables control of ROS/ROS2 robots through natural language commands by translating LLM instructions into ROS topics and services. Supports cross-platform WebSocket-based communication with existing robot systems without requiring code modifications.
Related MCP Servers
- AsecurityAlicenseAqualityFacilitates robotic movement control by providing functions that enable precise manipulation of linear and angular velocities through natural language commands, compatible with both ROS and ROS2.Last updated -2154PythonMIT License
- -securityFlicense-qualityA Python-based server that enables AI assistants to control robots by integrating the Model Context Protocol (MCP) with ROS 2, allowing for natural language commands that translate into robot movement via the /cmd\_vel topic.Last updated -56Python
- AsecurityAlicenseAqualityA server built on the Model Context Protocol that enables controlling the Unitree Go2 robot using natural language commands, which are translated into ROS2 instructions for the robot to perform corresponding actions.Last updated -1235PythonApache 2.0
- AsecurityFlicenseAqualityAn intelligent middleware system that enables natural language interactive control of Universal Robots collaborative robots, allowing users to connect to and control industrial robots through voice/text commands with MCP-compatible LLMs.Last updated -293Python