MCP 서버에 대한 내 비디오에 대한 동반자 저장소 :

• MCP Server for LLM 기반의 AI Agent(Claude Desktop, Cursor, Windsurf 등)를 위한 로봇 제어 -Direct keyboard control 수동 조작
• CLI AI Agent는 Claude, Gemini 또는 GPT 모델과 로봇을 제어하기 위해 직접 사용할 수 있습니다.

MCP에 대해 더 알고 싶다면 공식 MCP 문서 참조

이 저장소는 SO-ARM100 / 101 로봇과 함께 작업합니다. lerobot SO-101 설치 가이드에 대한 자세한 지침에 대한 로봇을 설정하는 방법.

업데이트! 이제 부분적으로 LeKiwi (만 팔, MCP를 통해 모바일 기본 제어 TBD)를 지원합니다. MCP 서버를 사용하여 로봇을 제어하는 간단한 에이전트도 추가했습니다. Claude, Gemini 및 GPT 모델을 지원합니다. 내 경험 Claude는 최고이며 GPT는 좋지 않습니다. Gemini는 사이입니다.

비디오와이 저장소를 출시 한 후, LeRobot은 원래 코드와 호환성을 깨는 라이브러리의 중요한 업데이트를 발표했습니다.

원본 코드를 사용하고 정확하게 비디오를 따르려면이 릴리스를 사용하십시오.

빠른 시작

##1. 종속 설치

SO-ARM100 Robot Control with MCP

A companion repository to my video about MCP server for the robot:

• MCP Server for LLM-based AI agents (Claude Desktop, Cursor, Windsurf, etc.) to control the robot
• Direct keyboard control for manual operation
• CLI AI Agent can use it directly to control the robot with Claude, Gemini or GPT model

If you want to know more about MCP refer to the official MCP documentation

This repository suppose to work with the SO-ARM100 / 101 robots. Refer to lerobot SO-101 setup guide for the detailed instructions on how to setup the robot.

Update! Now it partially supports LeKiwi (only arm, the mobile base control through MCP is TBD). I also added a simple agent that uses MCP server to control the robot. It supports Claude, Gemini and GPT models. In my experience Claude is the best and GPT is not so good, Gemini is in between.

After I released the video and this repository, LeRobot released a significant update of the library that breaks the compatibility with the original code.

If you want to use the original code and exactly follow the video, please use this release.

Quick Start

1. Install Dependencies

For simplicity I use simple pip instead of uv that is often recommended in MCP tutorials - it works just fine.

python -m venv .venv
source .venv/bin/activate  # or .venv\Scripts\activate on Windows
pip install -r requirements.txt

It may be required to install lerobot separately, just use the official instructions from the lerobot repository

2. Connect Your Robot

• Connect SO-ARM100 via USB
• Update config.py with your serial port for so-arm (e.g., /dev/tty.usbmodem58FD0168731) or robot_ip for lekiwi (e.g., 192.168.1.1)
• Connect cameras and update config.py with the correct indices and names (for lekiwi only names are important)

3. Use the robot

🔍 Check Robot Status and Calibration:

python check_positions.py

This will show you the current robot state without actual control. Move your robot manually to make sure it is properly calibrated and configured.

After the latest update, lerobot is using the normalized joints states instead of degrees. You can update MOTOR_NORMALIZED_TO_DEGREE_MAPPING in config.py to match your robot calibration. You will need to update these values every time you recalibrate the robot.

🎮 Manual Keyboard Control:

python keyboard_controller.py

Now you can try to control the robot manually using the keyboard. Test it before moving on to the MCP step, to make sure it works properly.

🛠️ MCP server in the dev mode

mcp dev mcp_robot_server.py