About myCobot MCP
myCobot MCP is an MCP server for sending simple pick-and-place instructions to myCobot. It is intended for setups with a camera and suction pump, and requires an MCP client that supports image feedback.
Key features
- 01Send pick-and-place instructions
- 02Use image feedback
- 03Configure camera and myCobot settings
Use cases
- 01Picking up and placing detected objects
- 02Connecting myCobot and camera through an MCP client
MCP support
The MCP server lets clients issue pick-and-place instructions to myCobot. The connected client must support image feedback.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEmyCobot MCP
Overview
This project is a MCP server for myCobot.
This MCP can send simple pick-and-place instructions to myCobot.
Note
This MCP server requires image feedback. Please connect an MCP client that can handle image feedback.
Chat example

https://github.com/user-attachments/assets/e2c222b8-1ce2-4fb1-8b59-11ec5e973432
Setup
DDS API Token
This project uses the DDS API for object detection. Please register and issue an API key for DDS.
https://cloud.deepdataspace.com/
Claude-Desktop
If you want to run this project on Ubuntu, you can install Claude-Desktop from the following instructions.
https://github.com/aaddrick/claude-desktop-debian
Edit the claude_desktop_config.json file to add the following:
{
"mcpServers": {
"mycobot": {
"command": "uvx",
"args": [
"mycobot-mcp",
"--settings-path",
"/path/to/settings.json"
],
"env": {
"DDS_API_TOKEN": "your-api-token"
}
}
}
}
Or you can clone this repository and run the following command.
git clone https://github.com/neka-nat/mycobot-mcp.git
{
"mcpServers": {
"mycobot": {
"command": "uv",
"args": [
"--directory",
"/path/to/mycobot-mcp/",
"run",
"mycobot-mcp",
"--settings-path",
"/path/to/settings.json"
],
"env": {
"DDS_API_TOKEN": "your-api-token"
}
}
}
}
Hardware
This software assumes the following hardware configuration.
Parameters
Create a settings.json file to configure the myCobot hardware and the camera.
The sample is here.
{
"camera_id": 0,
"camera_parameter_path": "/path/to/camera_calibration/mtx_dist.npy",
"mycobot_settings": {
"urdf_path": "/path/to/mycobot.urdf",
"end_effector_name": "camera_flange",
"port": "/dev/ttyACM0",
"baud": 115200,
"default_speed": 40,
"default_z_speed": 20,
"suction_pin": 5,
"command_timeout": 5,
"use_gravity_compensation": false,
"end_effector_height": 0.065,
"object_height": 0.01,
"release_height": 0.05,
"places": [
{
"name": "home",
"description": "Home position",
"position": [0, 20, -130, 20, 0, 0]
},
{
"name": "capture",
"description": "Camera capture position",
"position": [0, 0, -30, -60, 0, -45]
},
{
"name": "drop",
"description": "Position to drop object",
"position": [-45, 20, -130, 20, 0, 0]
}
]
}
}
Change port permission
When you connect mycobot, you need to change the permission.
sudo chmod 666 /dev/ttyACM0
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.