{
  "markdown": "# ROS MCP Server 🧠⇄🤖\n\n![Static Badge](https://img.shields.io/badge/ROS-Available-green)\n![Static Badge](https://img.shields.io/badge/ROS2-Available-green)\n![Static Badge](https://img.shields.io/badge/License-Apache%202.0-blue)\n![Python](https://img.shields.io/badge/python-3.10%2B-blue)\n![pip](https://img.shields.io/badge/pip-23.0%2B-blue)\n![Dev Container](https://img.shields.io/badge/Dev-Container%20Ready-blue)\n![GitHub Repo stars](https://img.shields.io/github/stars/robotmcp/ros-mcp-server?style=social)\n![GitHub last commit](https://img.shields.io/github/last-commit/robotmcp/ros-mcp-server)\n\n<!-- mcp-name: io.github.robotmcp/ros-mcp-server -->\n\n<p align=\"center\">\n  <img src=\"https://github.com/robotmcp/ros-mcp-server/blob/main/docs/images/framework.png\"/>\n</p>\n\nROS-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.  \n\n### Why ROS-MCP?\n\n- **No robot source code changes** → just add the `rosbridge` node to your existing ROS setup.\n- **True two-way communication** → LLMs can both *control* robots and *observe* everything happening on the Robot.\n- **Full context** → publish & subscribe to topics, call services & actions, set parameters, read sensor data, and monitor robot state in real time.\n- **Deep ROS understanding** → guides the LLM to discover available topics, services, actions, and their types (including custom ones) — enabling it to use them with the right syntax without manual configuration.\n- **Works with any MCP client** → built on the open [MCP standard](https://modelcontextprotocol.io/), supporting Claude Code, Codex CLI, Gemini CLI, Claude Desktop, ChatGPT, Cursor, and more.\n- **Works across ROS versions** → compatible across ROS 2 (Jazzy, Humble, and others) and ROS 1 distros.\n\n---\n## 🎥 Examples in Action  \n\n<p align=\"center\">\n  <a href=\"https://youtu.be/Yy1loJAn9sA\">\n    <img src=\"https://github.com/robotmcp/ros-mcp-server/blob/main/docs/images/MCP%20Demos%20Slide%20-%207to12s.gif\" alt=\"ROS MCP demos\" />\n  </a>\n</p>\n\n---\n🏭 **Example - AI Agent diagnosis of Industrial Robot End Effector** ([Video](https://youtu.be/EhZNFULz9P4))  \n- The MCP server connects Claude to a production industrial robot, with only the technician manuals as reference.\n- Claude discovers the robot's custom topic and service types and their syntax on its own.\n- From a single prompt to test the gripper, it reads the manuals, runs its own tests, finds an anomaly, and reports the root cause.\n\n<p align=\"center\">\n  <a href=\"https://youtu.be/EhZNFULz9P4\">\n    <img src=\"https://github.com/robotmcp/ros-mcp-server/blob/main/docs/images/ROS%20MCP%20Gripper%20vacuum%20test.jpg\" width=\"400\" alt=\"Testing and debugging an industrial robot\" />\n  </a>\n</p>\n\n---\n🤖 **Example - Controlling \"Wilson\" with natural language**  ([video](https://www.traceglarue.com/wilson))  \nFrom a single prompt — *\"Grab a Coke from the fridge & go to the living room.\"* — 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.\n\n<p align=\"center\">\n  <a href=\"https://www.traceglarue.com/wilson\">\n    <img src=\"https://github.com/robotmcp/ros-mcp-server/blob/main/docs/images/Wilson%20thumbnail.jpg\" width=\"400\" alt=\"Wilson robot controlled with natural language\" />\n  </a>\n</p>  \n\n---\n🐕 **Example - Controlling Unitree Go2 in NVIDIA Isaac Sim**  ([video](https://www.youtube.com/watch?v=9StFx4lnvmc))  \nThe MCP server connects Claude to a simulated Unitree Go2 quadruped in NVIDIA Isaac Sim, interpreting natural language commands to navigate and control the robot. \n\n<p align=\"center\">\n  <a href=\"https://www.youtube.com/watch?v=9StFx4lnvmc\">\n    <img src=\"https://img.youtube.com/vi/9StFx4lnvmc/maxresdefault.jpg\" width=\"400\" alt=\"Controlling Unitree Go2 in NVIDIA Isaac Sim\" />\n  </a>\n</p>  \n\n\n---\n\n## 🛠 Getting Started\n\nFollow the [installation guide](docs/install/installation.md) to get started.\n\nROS-MCP works with Claude Code, Codex CLI, Gemini CLI, Claude Desktop, ChatGPT, Cursor, or any MCP-compatible client.\n\n<p align=\"center\">\n  <img src=\"https://github.com/robotmcp/ros-mcp-server/blob/main/docs/images/MCP_topology.png\"/>\n</p>\n\n---\n\n## 📚 More Examples & Tutorials  \n\nBrowse our [examples](examples) to see the server in action.  \nWe welcome community PRs with new examples and integrations!  \n\n---\n\n## 🤝 Contributing  \n\nWe love contributions of all kinds:  \n- Bug fixes and documentation updates  \n- New features (e.g., Action support, permissions)  \n- Additional examples and tutorials  \n\nCheck out the [contributing guidelines](docs/contributing.md) and see issues tagged **good first issue** to get started.  \n\n---\n\n## 📜 License  \n\nThis project is licensed under the [Apache License 2.0](LICENSE).  \n",
  "bytes": 4862,
  "sha": "b9d36be96e8a12b6a8120bb3ab4a486be7d5042ed64047f711469d7ce6163bcd",
  "repo_slug": "robotmcp/ros-mcp-server",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_robotmcp_ros_mcp_server_aa9adc28/readme"
}