lpigeon/unitree-go2-mcp-server
by Various
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.
MCP
lpigeon/unitree-go2-mcp-server
Added 1 June 2026
Overview
The Unitree Go2 MCP Server is a Python-based server that exposes the Unitree Go2 robot's control interface through the Model Context Protocol. It translates natural language commands from a connected LLM into robot actions, enabling conversational control of the robot.
Best for
Best for
Developers and roboticists who want to experiment with LLM-driven control of a Unitree Go2 robot
Use cases
- Controlling a Unitree Go2 robot via voice or chat prompts
- Integrating robot movement and sensor feedback into LLM-driven workflows
- Prototyping interactive robot behaviors without writing low-level control code
How to use
Install
pip install uv Tools exposed
uvgitpip
Tested with
Claude Desktop
Example client config
{\n "mcpServers": {\n "unitree-go2-mcp-server": {\n "command": "uv",\n "args": [\n "--directory",\n "/ABSOLUTE/PATH/TO/PARENT/FOLDER/unitree-go2-mcp-server",\n "run",\n "server.py"\n ]\n }\n }\n} Notes
The Unitree Go2 MCP Server is a Python-based server that exposes the Unitree Go2 robot’s control interface through the Model Context Protocol. It translates natural language commands from a connected LLM into robot actions, enabling conversational control of the robot.
79 stars on GitHub. Last updated 2025-05-12. Licensed Apache-2.0.
Use cases
- Controlling a Unitree Go2 robot via voice or chat prompts
- Integrating robot movement and sensor feedback into LLM-driven workflows
- Prototyping interactive robot behaviors without writing low-level control code
Pros
- Enables natural language control of a physical robot
- Leverages the MCP standard for easy integration with LLM tools
- Open source with a growing community (79 stars)
Cons
- Requires a Unitree Go2 robot and a compatible LLM to function
- Limited to the capabilities exposed by the robot’s SDK
- Relatively new project with potentially sparse documentation
Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.
Pros
- Enables natural language control of a physical robot
- Leverages the MCP standard for easy integration with LLM tools
- Open source with a growing community (79 stars)
Cons
- Requires a Unitree Go2 robot and a compatible LLM to function
- Limited to the capabilities exposed by the robot's SDK
- Relatively new project with potentially sparse documentation
Pairs with
Other entries in the index that connect to this one. Click through to see the chain.
Get the free Developer’s Field Guide
A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.
Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.