Allows natural language control of quadruped robots within the NVIDIA Isaac Sim simulation environment.
Provides bidirectional communication with Robot Operating System (ROS/ROS2) for robot control, sensor monitoring, topic publishing/subscribing, service calls, action executions, and parameter tuning.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@ROS & LLM Integration Bridge Tell the robot to navigate to the living room"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Empowering robots with Large Language Models for seamless, bidirectional communication.[cite: 1]
🚫 Zero Modifications Required: Easily integrate the rosbridge node without altering your existing robot source code.[cite: 1]
🔄 True Bidirectional Interaction: LLMs can both control the robot's actions and monitor its environment in real-time.[cite: 1]
🧠 Comprehensive Context Awareness: Gain full access to publish/subscribe topics, service calls, action executions, sensor readings, and parameter tuning.[cite: 1]
🔍 Intelligent Discovery: The system automatically guides the AI to understand available ROS topics, custom types, and services, ensuring flawless syntax execution.[cite: 1]
🌐 Universal Client Support: Built on the open MCP standard, making it fully compatible with Claude, Gemini, ChatGPT, Cursor, and Codex CLI.[cite: 1]
⚡ Cross-Version Compatibility: Works flawlessly across ROS 1 and ROS 2 distributions (including Jazzy and Humble).[cite: 1]
Related MCP server: ROS2 MCP Server
Connects AI agents to production robots using only technical manuals as a reference. The AI autonomously discovers custom topic syntaxes, executes diagnostic tests (like vacuum/gripper tests), identifies anomalies, and reports the root cause.[cite: 1]
Command your mobile robots with simple phrases like, "Grab a Coke from the fridge & go to the living room." The AI utilizes Nav2 (SLAM) for mapping/navigation and MoveIt for manipulation, operating entirely autonomously.[cite: 1]
Interpret natural language commands to navigate and control quadruped robots directly within the NVIDIA Isaac Sim environment.[cite: 1]
To start integrating LLMs with your ROS setup, please refer to our Installation Guide.[cite: 1]
This tool is ready to be paired with any MCP-compatible client, including Claude Desktop, Gemini CLI, ChatGPT, and Cursor.[cite: 1]
We encourage community contributions to make this project even better:
🐛 Bug fixes and documentation improvements
✨ New features (e.g., advanced permissions, action support)
📖 Additional tutorials and real-world examples
Please review our Contributing Guidelines to get started.[cite: 1]
This software is released under the Apache License 2.0.[cite: 1]
This server cannot be deployed
Connect Claude, Cursor, Codex, and other AI tools to your robotics mission data.
Operate Linux, macOS and Windows from your LLM. Every action runs through an auditable allowlist.
Build, validate, and deploy multi-agent AI solutions from any AI environment.
