What hardware is required for myCobot MCP?
A myCobot robot, a suction-pump, and a camera-flange are needed. The software expects specific poses and calibration files.
@neka-nat
Basic information
myCobot MCP(Model Context Protocol) server
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"mycobot": {
"command": "uvx",
"args": [
"mycobot-mcp",
"--settings-path",
"/path/to/settings.json"
],
"env": {
"DDS_API_TOKEN": "your-api-token"
}
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
Fetch the live tool list by running this server in a temporary sandbox using the button above.
myCobot MCP is an MCP server for the myCobot robotic arm. It enables sending simple pick-and-place instructions to the robot. The server requires image feedback, so it must be used with an MCP client that can handle image data. Object detection is powered by the DDS API.
Configure the server by setting a DDS API token as an environment variable and providing a settings.json file with hardware parameters. For Claude Desktop, edit claude_desktop_config.json to run uvx mycobot-mcp --settings-path /path/to/settings.json (or use uv from a cloned repository). After connecting the myCobot, change the port permission with sudo chmod 666 /dev/ttyACM0.
A myCobot robot, a suction-pump, and a camera-flange are needed. The software expects specific poses and calibration files.
Register at [cloud.deepdataspace.com](https://cloud.deepdataspace.com/) and issue an API key. Provide it via the `DDS_API_TOKEN` environment variable.
Yes. The server requires image feedback, so connect an MCP client that can handle image data.
It configures the camera ID, calibration path, robot URDF, end effector, communication port, baud rate, joint speeds, suction pin, and predefined positions (home, capture, drop).
Run `sudo chmod 666 /dev/ttyACM0` after connecting the robot to allow the server to communicate over the serial port.
不止于 CSS
A curated list of references for MLOps

See and control a real Windows PC you own — from any MCP client, locally or remotely. Observe (UIA + screenshots), click/type/drag/scroll, launch apps, owner Live View. BYOH: your machine, your key.
This open-source curriculum introduces the fundamentals of Model Context Protocol (MCP) through real-world, cross-language examples in .NET, Java, TypeScript, JavaScript, Rust and Python. Designed for developers, it focuses on practical techniques for building modular, scalable,
AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents
Comments