"17",{"name":"twitter:image","content":"https://mcp.so/logo.png"}]],"error":null,"digest":"$undefined"} e:{"metadata":"$14:metadata","error":null,"digest":"$undefined"} 28:I[60719,["7626","static/chunks/f6ab4fea-4425dae3da7674a3.js","8548","static/chunks/b27dc69b-e5acb70cd9d66ddf.js","5232","static/chunks/5232-db5923cda78a4960.js","6465","static/chunks/6465-6b79f1dc957ae3f4.js","9388","static/chunks/9388-d1a745fd53a10850.js","4902","static/chunks/4902-40271c136eb736f1.js","1508","static/chunks/1508-abbc58115cbb4fd0.js","6125","static/chunks/6125-6f7cbc86df4f2503.js","7771","static/chunks/7771-66979ce602088329.js","7660","static/chunks/7660-f5d56ac6a9ee6cc8.js","4147","static/chunks/4147-ef3df161a800b88b.js","9783","static/chunks/9783-e1d5b54e9718b38b.js","8084","static/chunks/8084-f1229cc5d0501fe0.js","2024","static/chunks/2024-e03e13f5faa34f45.js","7796","static/chunks/app/%5Blocale%5D/(default)/server/%5Bname%5D/%5Bauthor_name%5D/page-c3a3facf548ee943.js"],"default"] 29:Tc48,## Overview ![Static Badge](https://img.shields.io/badge/ROS-Available-green) ![Static Badge](https://img.shields.io/badge/ROS2-Available-green) [![smithery badge](https://smithery.ai/badge/@lpigeon/ros_mcp_server)](https://smithery.ai/server/@lpigeon/ros_mcp_server) ![Static Badge](https://img.shields.io/badge/license-MIT-blue)

The ROS MCP Server is designed to facilitate the control of robotic movement by providing a set of functions that allow for precise manipulation of linear and angular velocities. This enables the robot to perform complex maneuvers and navigate through various environments efficiently. ## Installation ### Installing via Smithery To install ros_mcp_server for Claude Desktop automatically via [Smithery](https://smithery.ai/server/@lpigeon/ros_mcp_server): ```bash npx -y @smithery/cli install @lpigeon/ros_mcp_server --client claude ``` ### Installing Locally ### `uv` Installation - To install `uv`, you can use the following command: ```bash curl -LsSf https://astral.sh/uv/install.sh | sh ``` or ```bash pip install uv ``` - Create virtual environment and activate it (Optional) ```bash uv venv source .venv/bin/activate ``` ### MCP Server Configuration Set MCP setting to mcp.json. ```bash "ros_mcp_server": { "command": "uv", "args": [ "--directory", "/ABSOLUTE/PATH/TO/PARENT/FOLDER/ros_mcp_server",, "run", "server.py" ] } ``` ## MCP Functions ### pub_twist - **Purpose**: Sends movement commands to the robot by setting linear and angular velocities. - **Parameters**: - `linear`: Linear velocity (List[Any]) - `angular`: Angular velocity (List[Any]) ### pub_twist_seq - **Purpose**: Sends a sequence of movement commands to the robot, allowing for multi-step motion control. - **Parameters**: - `linear`: List of linear velocities (List[Any]) - `angular`: List of angular velocities (List[Any]) - `duration`: List of durations for each step (List[Any]) ## How To Use ### 1. Set IP and Port to connect rosbridge. - Open `server.py` and change your `LOCAL_IP`, `ROSBRIDGE_IP` and `ROSBRIDGE_PORT`. (`ROSBRIDGE_PORT`'s default value is `9090`) ### 2. Run rosbridge server. ROS 1 ```bash roslaunch rosbridge_server rosbridge_websocket.launch ``` ROS 2 ```bash ros2 launch rosbridge_server rosbridge_websocket_launch.xml ``` ### 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.

Ros_mcp_server

ツール