ROS MCP Server

What is ROS MCP Server about?

ROS MCP Server connects large language models such as Claude, GPT or Gemini with robots that run ROS or ROS2. It creates a two‑way communication channel so LLMs can both issue commands to the robot and observe its sensing data, topics, services and parameters without modifying the robot’s existing source code.

How to use ROS MCP Server?

1. Setup – Clone the repository, install the uv package manager, and add the rosbridge node to the robot.
2. Install – Follow the docs/installation.md steps to install Python dependencies (Python 3.10+ required).
3. Start ROS bridge – Run rosbridge on the robot (ROS1: roslaunch rosbridge_server rosbridge_websocket.launch; ROS2: ros2 launch rosbridge_server rosbridge_websocket_launch.xml).
4. Connect an MCP‑enabled LLM client – Configure Claude Desktop, Gemini, ChatGPT or any MCP‑compatible client to point to the ROS MCP Server’s WebSocket URL.
5. Interact – Use natural language prompts; the server translates them into ROS topics, services, parameter changes or publishes/subscribes as needed.

Key features of ROS MCP Server

• No robot code changes required – only the rosbridge node is needed.
• Bidirectional communication – LLMs can both control and observe the robot.
• ROS1 & ROS2 support – works out‑of‑the‑box with both versions.
• Full ROS introspection – list topics, services, message types, view definitions, publish/subscribe, call services, get/set parameters.
• Future extensions – planned ROS Action support and permission controls.

Use cases of ROS MCP Server

• Natural‑language robot teleoperation – operators issue spoken commands to drive mobile manipulators or quadrupeds.
• Real‑time robot monitoring – LLMs read sensor streams and system diagnostics to provide status reports.
• Debugging and testing – engineers query custom topics/services and invoke them via natural language without writing code.
• Simulation integration – control simulated robots in NVIDIA Isaac Sim using LLM prompts.

FAQ from the ROS MCP Server

Q: Do I need to modify existing robot packages? A: No. Adding the standard rosbridge node is sufficient.

Q: Which Python version is required? A: Python 3.10 or newer.

Q: Can I use this with proprietary LLMs? A: Yes, any model that supports the Model Context Protocol (MCP) can connect.

Q: Is ROS Action support available now? A: It is planned for a future release.

Q: How are permissions managed? A: Permission controls are also slated for a future update.

ROS MCP Server 🧠⇄🤖

ROS-MCP-Server connects large language models (such as Claude, GPT, and Gemini) with existing robots giving them bidirectional AI integration.

With no changes to existing robot source code, this enables:

• 🗣 Commanding the robot in natural language → instructions are translated into ROS/ROS2 commands.
• 👀 Giving AI full visibility → subscribe to topics, call services, read sensor data, and monitor robot state in real time.

✅ Key Benefits

• No robot code changes → only requires adding the rosbridge node.
• True two-way communication → LLMs can both control robots and observe everything happening in ROS (sensors, topics, parameters).
• ROS1 & ROS2 support → works with both versions out of the box.
• MCP-compatible → integrates with any MCP-enabled LLM (Claude Desktop, Gemini, ChatGPT, and beyond).

🎥 Examples in Action

🖥️ Example - Controlling the MOCA mobile manipulator in NVIDIA Isaac Sim
Commands are entered into Claude Desktop, which uses the MCP server to directly drive the simulated robot.

---

🐕 Example - Controlling Unitree Go with natural language (video)
The MCP server enables the Claude to interpret images from the robot's cameras, and then command the robot based on human natural language commands.

---

🏭 Example - Debugging an industrial robot (Video)

• Connecting to an industrial robot enables the LLM to browse all ROS topics and services to assess the robot state.
• With no predefined context, the MCP server enables the LLM to query details about custom topic and service types and their syntax (00:28).
• Using only natural language, the operator calls the custom services to test and debug the robot(01:42).

---

⚙️ Features of the ROS MCP Server

• List topics, services, and message types → explore everything available in your robot’s ROS environment.
• View type definitions (incl. custom) → understand the structure of any message.
• Publish/subscribe to topics → send commands or stream robot data in real time.
• Call services (incl. custom) → trigger robot functions directly.
• Get/set parameters → read or adjust robot settings on the fly.
• 🔜 Action support → upcoming support for ROS Actions.
• 🔜 Permission controls → manage access for safer deployments.

---

🛠 Getting Started

The MCP server is version-agnostic (ROS1 or ROS2) and works with any MCP-compatible LLM.

Installation

Follow the installation guide for step-by-step instructions:

1. Clone the repository
2. Install uv and rosbridge
3. Install Claude Desktop (or any MCP-enabled client)
4. Configure your client to connect to the ROS MCP Server
5. Start rosbridge on the target robot

---

📚 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.

---

📜 License

This project is licensed under the Apache License 2.0.