Skip to content
Back to search

unitree-go2-mcp-server

The Unitree Go2 MCP Server is a server built on the MCP that enables users to control the Unitree Go2 robot using natural language commands interpreted by a LLM.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/lpigeon--unitree-go2-mcp-server/badge.svg)](/listings/lpigeon--unitree-go2-mcp-server)

HTML

<a href="/listings/lpigeon--unitree-go2-mcp-server"><img src="/api/listings/lpigeon--unitree-go2-mcp-server/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

These steps run a script from the network that findsafeskills does not scan.

1. Setup `unitree_ros2` environment

https://github.com/unitreerobotics/unitree_ros2

- **You need to complete the setup up to `Step 2: Connect and test` in the repository linked above.**

2. Clone this repository

git clone https://github.com/lpigeon/unitree-go2-mcp-server.git
cd unitree-go2-mcp-server

3. `uv` Installation

- To install `uv`, you can use the following command:

curl -LsSf https://astral.sh/uv/install.sh | sh

or

pip install uv

- Create virtual environment and activate it (Optional)

uv venv
source .venv/bin/activate

4. MCP Server Configuration

Set MCP setting to mcp.json.

**Please keep in mind that the configuration must be done on the PC connected to the Go2.**

{
    "mcpServers": {
        "unitree-go2-mcp-server": {
            "command": "uv",
            "args": [
              "--directory",
              "/ABSOLUTE/PATH/TO/PARENT/FOLDER/unitree-go2-mcp-server",
              "run",
              "server.py"
            ]
        }
    }
}

If you use Claude Desktop, you can find mcp.json using the following command:

- MacOS

code ~/Library/Application\ Support/Claude/claude_desktop_config.json

- Linux(Ubuntu)

You can install Claude Desktop to use [claude-desktop-debian](https://github.com/aaddrick/claude-desktop-debian).

code ~/.config/Claude/claude_desktop_config.json

- Windows

code $env:AppData\Claude\claude_desktop_config.json

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 134 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. # Unitree Go2 MCP Server
  2. ![ROS 2](https://img.shields.io/badge/ROS_2-Foxy|Humble-blue)
  3. ![Static Badge](https://img.shields.io/badge/License-Apache2.0-green)
  4. <center><img src="https://github.com/lpigeon/unitree-go2-mcp-server/blob/main/img/thumbnail.png" width="800"/></center>
  5. The **Unitree Go2 MCP Server** is a server built on the Model Context Protocol (MCP) that enables users to control the Unitree Go2 robot using natural language commands interpreted by a Large Language Model (LLM). These commands are translated into ROS2 instructions, allowing the robot to perform corresponding actions.
  6. ## Requirements
  7. - **Unitree Go2 robot**
  8. - **Ubuntu 20.04 or 22.04**
  9. - **ROS2 environment** : [Humble](https://docs.ros.org/en/humble/Installation.html)(recommended) or [Foxy](https://docs.ros.org/en/foxy/Installation.html)
  10. ## MCP Functions
  11. You can find the list of functions in the [MCPFUNCTIONS.md](MCPFUNCTIONS.md).
  12. ## Installation
  13. ### 1. Setup `unitree_ros2` environment
  14. https://github.com/unitreerobotics/unitree_ros2
  15. - **You need to complete the setup up to `Step 2: Connect and test` in the repository linked above.**
  16. ### 2. Clone this repository
  17. ```bash
  18. git clone https://github.com/lpigeon/unitree-go2-mcp-server.git
  19. cd unitree-go2-mcp-server
  20. ```
  21. ### 3. `uv` Installation
  22. - To install `uv`, you can use the following command:
  23. ```bash
  24. curl -LsSf https://astral.sh/uv/install.sh | sh
  25. ```
  26. or
  27. ```bash
  28. pip install uv
  29. ```
  30. - Create virtual environment and activate it (Optional)
  31. ```bash
  32. uv venv
  33. source .venv/bin/activate
  34. ```
  35. ### 4. MCP Server Configuration
  36. Set MCP setting to mcp.json.
  37. **Please keep in mind that the configuration must be done on the PC connected to the Go2.**
  38. ```bash
  39. {
  40. "mcpServers": {
  41. "unitree-go2-mcp-server": {
  42. "command": "uv",
  43. "args": [
  44. "--directory",
  45. "/ABSOLUTE/PATH/TO/PARENT/FOLDER/unitree-go2-mcp-server",
  46. "run",
  47. "server.py"
  48. ]
  49. }
  50. }
  51. }
  52. ```
  53. If you use Claude Desktop, you can find mcp.json using the following command:
  54. - MacOS
  55. ```bash
  56. code ~/Library/Application\ Support/Claude/claude_desktop_config.json
  57. ```
  58. - Linux(Ubuntu)
  59. You can install Claude Desktop to use [claude-desktop-debian](https://github.com/aaddrick/claude-desktop-debian).
  60. ```bash
  61. code ~/.config/Claude/claude_desktop_config.json
  62. ```
  63. - Windows
  64. ```bash
  65. code $env:AppData\Claude\claude_desktop_config.json
  66. ```
  67. ## How To Use
  68. ### 1. Set `UNITREE_ROS2_SETUP_SH_PATH`.
  69. - Open `server.py` and change your `UNITREE_ROS2_SETUP_SH_PATH` (eg. `/home/lpigeon/unitree_ros2/setup.sh`)
  70. #### If you use `rosbridge`, you need Set IP and Port to connect rosbridge (Optional).
  71. - Open `server.py` and change your `LOCAL_IP`, `ROSBRIDGE_IP` and `ROSBRIDGE_PORT`. (`ROSBRIDGE_PORT`'s default value is `9090`)
  72. ### 2. Check the Go2 robot is connected to the network.
  73. Type the following command in the terminal.
  74. ```bash
  75. ros2 topic list
  76. ```
  77. You should see the following topic:
  78. ```bash
  79. /wirelesscontroller
  80. ```
  81. **If you don't see the topic, check the connection between the Go2 robot and the network.**
  82. ### 3. Run any AI system that has imported `unitree-go2-mcp-server`.
  83. ### 4. Type "Make the Go2 robot move forward at a velocity of 0.5 m/s for 3 seconds.".
  84. <center><img src="https://github.com/lpigeon/unitree-go2-mcp-server/blob/main/img/how_to_use_1.png" width="500"/></center>
  85. ### 5. Check the Go2 robot's movement.
  86. <center><img src="https://github.com/lpigeon/unitree-go2-mcp-server/blob/main/img/how_to_use_2.gif" width="500"/></center>
  87. ### 6. Type what you want to do and Enjoy!
  88. ## Contextual Understanding
  89. When you type a command like "It looks like the Go2 is getting tired," the LLM interprets this contextually — understanding that the robot might need a break or some form of stretching!
  90. <center><img src="https://github.com/lpigeon/unitree-go2-mcp-server/blob/main/img/contextual_understanding.gif" width="800"/></center>
  91. ## Simple Task
  92. This task is a comprehensive demo task showcasing the Unitree Go2 robot's obstacle avoidance, direction changing, and user interaction capabilities.
  93. <center><img src="https://github.com/lpigeon/unitree-go2-mcp-server/blob/main/img/task_test.gif" width="800"/></center>
  94. ## Contributing
  95. Contributions are welcome!
  96. Whether you're fixing a typo, adding a new function, or suggesting improvements, your help is appreciated.
  97. Please follow the [contributing guidelines](CONTRIBUTING.md) for more details on how to contribute to this project.

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.