Ros MCP Server

🚀 ROS MCP Server

The ROS MCP Server is designed to empower robots to execute complex tasks and adapt to diverse environments effectively. It converts natural language commands input by users via LLM into ROS commands to control robots, and works with both ROS and ROS2 systems through rosbridge, enabling wide - spread application across multiple platforms with WebSocket communication.

✨ Features

Supported Message Types

• geometry_msgs/Twist
• sensor_msgs/Image

📦 Installation

Installation via Smithery

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

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

Local Installation

uv Installation

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

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

Or

pip install uv

• Create and activate a virtual environment (optional)

uv venv
source .venv/bin/activate

MCP Server Configuration

Configure MCP in mcp.json.

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

If you are using Claude Desktop, you can find mcp.json using the following commands:

• MacOS/Linux

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

• Windows

code $env:AppData\Claude\claude_desktop_config.json

💻 Usage Examples

MCP Functions

get_topics

• Purpose: Retrieve the list of available topics in the robot's ROS system.
• Return: List of topics (List[Any])

pub_twist

• Purpose: Send a motion command to the robot by setting linear and angular velocities.
• Parameters:
  • linear: Linear velocity (List[Any])
  • angular: Angular velocity (List[Any])

pub_twist_seq

• Purpose: Send a series of motion commands to the robot, allowing 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])

sub_image

• Purpose: Subscribe to and receive image data from the robot's camera topic.
• Return: Received image data (Image)

Usage Guide

1. Set IP and Port: Configure the IP address and port number in the ROS system as needed.
2. Run the Server: Start the MCP server to begin processing commands.
3. Send Commands: Control the robot by calling MCP functions.

📚 Documentation

Simulation Test

In the NVIDIA Isaac Sim environment, effective control and response of the robot are demonstrated.