WiseVision ROS 2

v1.0.0Browser Automationstable

Public implementation of MCP for ROS 2 enabling to interact with system visible various robots, capable of: List available topics List available services Call service Subscribe topic to get messages Publish message on topic and more

aimcpmcp-servermcp-server-ros2ros2
Share:
77
Stars
0
Downloads
0
Weekly
0/5

What is WiseVision ROS 2?

WiseVision ROS 2 is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to public implementation of mcp for ros 2 enabling to interact with system visible various robots, capable of: list available topics list available services call service subscribe topic to get messages p...

Public implementation of MCP for ROS 2 enabling to interact with system visible various robots, capable of: List available topics List available services Call service Subscribe topic to get messages Publish message on topic and more

This server falls under the Browser Automation category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • Public implementation of MCP for ROS 2 enabling to interact

Use Cases

ROS 2 topic and service management
Robot system interaction
Message publish and subscribe
wise-vision

Maintainer

LicenseMozilla Public License 2.0
Languagepython
Versionv1.0.0
UpdatedMay 13, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx wisevision-mcp-server-ros-2

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use WiseVision ROS 2

WiseVision ROS 2 MCP Server is a Python implementation of the Model Context Protocol for Robot Operating System 2 (ROS 2), enabling AI assistants like Claude to interact directly with robots and robotic systems through natural language. It exposes tools for listing topics and services, subscribing to and publishing messages on topics, calling services, managing ROS 2 actions (sending goals, collecting feedback, cancelling goals), and querying message type schemas. Robotics developers, researchers, and students can use it to debug robot behavior, analyze live sensor data, send movement commands, and orchestrate multi-step robot workflows entirely through conversational AI — without needing to write ROS 2 boilerplate code manually.

Prerequisites

  • ROS 2 installed (Humble or Jazzy supported)
  • Python 3 with uv package manager installed
  • A running ROS 2 environment with nodes, topics, and/or services active
  • An MCP-compatible client such as Claude Desktop, VS Code Copilot, or Warp terminal
  • Docker (optional — a pre-built Docker image is available for quick deployment)
1

Source your ROS 2 environment

Before starting the MCP server, source your ROS 2 installation so that the server process has access to ROS 2 Python bindings and can discover nodes, topics, and services.

source /opt/ros/humble/setup.bash
# Or for Jazzy:
# source /opt/ros/jazzy/setup.bash
2

Clone the repository

Clone the ros2_mcp repository from WiseVision to your local machine.

git clone https://github.com/wise-vision/ros2_mcp.git
cd ros2_mcp
3

Configure Claude Desktop to use the ROS 2 MCP server

Add the server to your claude_desktop_config.json. The server uses stdio transport and uv to run the mcp_ros_2_server module from the cloned directory. Replace /path/to/ros2_mcp with the absolute path to your clone.

{
  "mcpServers": {
    "ros2": {
      "command": "uv",
      "args": ["--directory", "/path/to/ros2_mcp", "run", "mcp_ros_2_server"]
    }
  }
}
4

Alternatively, use the Docker image

A pre-built Docker image is available on Docker Hub for quick deployment without a local Python setup. See the project's installation guide for Docker-specific configuration.

docker pull mcp/server/ros2
5

Verify topic and service discovery

With your ROS 2 nodes running, ask Claude to list available topics or services. The server auto-discovers everything visible in the ROS 2 graph, including message/service type schemas.

6

Use built-in prompts for common workflows

The server ships pre-built prompts (base.ros2-topic-echo-and-analyze, base.ros2-node-health-check, base.ros2-topic-relay, base.ros2-topic-diff-monitor) accessible from your MCP client for common robotics analysis tasks.

WiseVision ROS 2 Examples

Client configuration

Claude Desktop configuration to connect to the ROS 2 MCP server via uv from the cloned repository.

{
  "mcpServers": {
    "ros2": {
      "command": "uv",
      "args": ["--directory", "/home/user/ros2_mcp", "run", "mcp_ros_2_server"]
    }
  }
}

Prompts to try

Natural language commands for interacting with robots through the ROS 2 MCP server.

- "List all available ROS 2 topics and their message types"
- "Subscribe to /cmd_vel for 5 seconds and show me what velocity commands are being sent"
- "Publish a Twist message to /cmd_vel to move the robot forward at 0.5 m/s"
- "List all available ROS 2 services"
- "Call the /robot_state service and tell me the current robot state"
- "Check if my robot's expected topics and services are all online and healthy"
- "Subscribe to /camera/image_raw and analyze the message rate"

Troubleshooting WiseVision ROS 2

Server fails to start with 'No module named rclpy' or similar ROS 2 import errors

The server process must have the ROS 2 Python environment sourced. Ensure you source /opt/ros/<distro>/setup.bash before starting Claude Desktop, or configure the MCP entry to run under a shell that sources ROS 2 first (e.g. wrap the command in a shell script that sources and then runs uv).

No topics or services are discovered even though ROS 2 nodes are running

Verify the MCP server process and your ROS 2 nodes share the same ROS_DOMAIN_ID environment variable (default is 0). If you use a custom domain ID, set ROS_DOMAIN_ID in the MCP server's env config to match.

Service calls with custom message types fail with 'type not found'

For custom (non-standard) message types, source the workspace that defines those types before starting the MCP server (e.g. source ~/my_ws/install/setup.bash). The server must have those type definitions in its environment at startup time.

Frequently Asked Questions about WiseVision ROS 2

What is WiseVision ROS 2?

WiseVision ROS 2 is a Model Context Protocol (MCP) server that public implementation of mcp for ros 2 enabling to interact with system visible various robots, capable of: list available topics list available services call service subscribe topic to get messages publish message on topic and more It connects AI assistants to external tools and data sources through a standardized interface.

How do I install WiseVision ROS 2?

Follow the installation instructions on the WiseVision ROS 2 GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with WiseVision ROS 2?

WiseVision ROS 2 works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is WiseVision ROS 2 free to use?

Yes, WiseVision ROS 2 is open source and available under the Mozilla Public License 2.0 license. You can use it freely in both personal and commercial projects.

Browse More Browser Automation MCP Servers

Explore all browser automation servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "wisevision-mcp-server-ros-2": { "command": "npx", "args": ["-y", "wisevision-mcp-server-ros-2"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use WiseVision ROS 2?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides