About MCP Cobot Server
MCP Cobot Server is a FastMCP server for the M5 MyCobot280 robot, intended for integration with collaborative robot systems. It exposes joint controls, home-position actions, LED color changes, and description-based dance routines.
Key features
- 01Read servo joint angles
- 02Control one or all joints
- 03Set or move to the home position
- 04Change the LED matrix color
- 05Run description-based dance routines
- 06Release all servos
Use cases
- 01Check the robot's current joint angles
- 02Move a joint or adjust all joints
- 03Set the robot to its home position
- 04Run a dance combining joint movement and LED changes
MCP support
The FastMCP server exposes MyCobot280 joint, home, LED, and dance controls to MCP clients.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEMCP Cobot Server
This repository contains the MCP Cobot Server, a FastMCP server implementation for the M5 MyCobot280 robot.
Based on the model context protocol python-sdk: https://github.com/modelcontextprotocol/python-sdk?tab=readme-ov-file#quickstart
Features
- Implements the MCP standard for efficient context management.
- Built with FastMCP for high performance and scalability.
- Designed for integration with collaborative robot (myCobot) systems.
Requirements
- Python 3.8+
- FastMCP library
Installation
-
Clone the repository:
git clone https://github.com/your-username/mcp-cobot-server.git cd mcp-cobot-server -
Install dependencies:
uv sync source .venv/bin/activate
Note This project uses uv to install manage the python virtual environment and dependencies. Learn more here: https://docs.astral.sh/uv/guides/projects/
Usage
Start the server:
# launch a standalone MCP server with:
uvx mcpo --port 8000 -- uv run --with mcp[cli] --with pymycobot mcp run ./server.py
# Install the mcp profile with claude
mcp install server.py
For development:
# debug the mcp interface
mcp dev server.py
Available Functions
The following functions are exposed to mcp.tool in server.py:
get_angles: Retrieves the current angles of all servos.move_angle: Moves a specific joint (servo) to a target angle at a specified speed.move_angles: Moves all joints to specified angles at a given speed.go_home: Moves all joints to a predefined "home" position.set_home: Sets the current joint angles as the new "home" position.change_color: Changes the LED matrix color of the robot.relax: Releases all servos, allowing the robot arms to relax.interpretive_dance_routine: Executes a creative dance routine based on a description, involving joint movements and LED color changes.
MyCobot M5 280
The myCobot SDK I'm using is documented here: https://github.com/elephantrobotics/pymycobot/blob/main/docs/MyCobot_280_en.md The robot I'm using is here: Elephant Robotics myCobot 280 M5Stack 2023 - 6 DOF Collaborative Robot
Joint ranges
| Joint Id | Range |
|---|---|
| 1 | -168 ~ 168 |
| 2 | -135 ~ 135 |
| 3 | -150 ~ 150 |
| 4 | -145 ~ 145 |
| 5 | -165 ~ 165 |
| 6 | -180 ~ 180 |
Contributing
Contributions are welcome! Please open an issue or submit a pull request.
License
This project is licensed under the MIT License. See the LICENSE file for details.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.