ROS MCP Server πŸ§ β‡„πŸ€–

MCP serverAI & models

Add this and AI models like Claude and ChatGPT can connect with robots that run ROS. Once it is in place, your AI opens a direct line to a ROS robot and can communicate with it from a regular conversation. It is a community-maintained addition to your AI's abilities.

Unavailable. This server has no hosted endpoint yet, so Ahel can't serve it.

Add to setup to save this item as a reference. Ahel cannot run it, and signing in will not install it.

What your AI can do with it

  • Connect Claude to a ROS robot
  • Connect ChatGPT to a ROS robot
  • Communicate with a ROS robot from your AI conversation
  • Bring robots that run ROS within your AI assistant's reach

Getting started

  1. Save this item in Your setup as a reference.
  2. Read the source or reference documentation for its setup requirements. Saving it here does not connect it to your AI.
  3. Check this page for availability before trying to install it through Ahel.

From the project's README

As published by robotmcp/ros-mcp-server in README.md.

ROS-MCP-Server connects large language models (such as Claude, GPT, and Gemini) to robots, enabling bidirectional communication with no changes to existing robot source code.

Why ROS-MCP?

  • No robot source code changes β†’ just add the rosbridge node to your existing ROS setup.
  • True two-way communication β†’ LLMs can both control robots and observe everything happening on the Robot.
  • Full context β†’ publish & subscribe to topics, call services & actions, set parameters, read sensor data, and monitor robot state in real time.
  • Deep ROS understanding β†’ guides the LLM to discover available topics, services, actions, and their types (including custom ones) β€” enabling it to use them with the right syntax without manual configuration.
  • Works with any MCP client β†’ built on the open MCP standard, supporting Claude Code, Codex CLI, Gemini CLI, Claude Desktop, ChatGPT, Cursor, and more.
  • Works across ROS versions β†’ compatible across ROS 2 (Jazzy, Humble, and others) and ROS 1 distros.

πŸŽ₯ Examples in Action


🏭 Example - AI Agent diagnosis of Industrial Robot End Effector (Video)

  • The MCP server connects Claude to a production industrial robot, with only the technician manuals as reference.
  • Claude discovers the robot's custom topic and service types and their syntax on its own.
  • From a single prompt to test the gripper, it reads the manuals, runs its own tests, finds an anomaly, and reports the root cause.

πŸ€– Example - Controlling "Wilson" with natural language (video)
From a single prompt β€” "Grab a Coke from the fridge & go to the living room." β€” Google Gemini uses the MCP server to navigate and manipulate autonomously. Built on ROS 2 with Nav2 (SLAM) for mapping and navigation, and MoveIt to command the manipulator.


πŸ• Example - Controlling Unitree Go2 in NVIDIA Isaac Sim (video)
The MCP server connects Claude to a simulated Unitree Go2 quadruped in NVIDIA Isaac Sim, interpreting natural language commands to navigate and control the robot.


πŸ›  Getting Started

Follow the installation guide to get started.

ROS-MCP works with Claude Code, Codex CLI, Gemini CLI, Claude Desktop, ChatGPT, Cursor, or any MCP-compatible client.


πŸ“š More Examples & Tutorials

Browse our examples to see the server in action.
We welcome community PRs with new examples and integrations!


🀝 Contributing

We love contributions of all kinds:

  • Bug fixes and documentation updates
  • New features (e.g., Action support, permissions)
  • Additional examples and tutorials

Check out the contributing guidelines and see issues tagged good first issue to get started.


πŸ“œ License

This project is licensed under the Apache License 2.0.

Signals

GitHub stars
1k
Forks
213
Last commit
Oct 2026
Weekly downloads
42

What people say

The posts are mostly release announcements and hype, but a couple of users describe actually using it to control robots via natural language, including semantic navigation ('go near the TV') with no robot code changes. No recurring complaints appear anywhere in the posts; the reports are uniformly positive but thin on hands-on detail.

Praised for
natural language control without modifying robot code
works with ROS 1 & 2 and multiple LLMs (Claude, GPT, Gemini)
real demos of semantic navigation and robot vision tasks

Summarized from 14 public posts. Opinions are theirs, not Ahel's.

Advanced
Delivery
ros-mcp-server MCP server β†’ your Ahel connector (mcp.ahel.ai) β†’ your AI.
Item type
mcp-server
Key
io-github-robotmcp-ros-mcp-server
Source
github.com/robotmcp/ros-mcp-server