myCobot MCP

Name: myCobot MCP
Author: neka-nat

@neka-nat

リポジトリ

myCobot MCP について

myCobot MCP(Model Context Protocol) server

#mcp #claude #mycobot #mcp-server

基本情報

カテゴリ

その他

ライセンス

MIT

ランタイム

python

トランスポート

stdio

公開者

neka-nat

設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "mycobot": {
      "command": "uvx",
      "args": [
        "mycobot-mcp",
        "--settings-path",
        "/path/to/settings.json"
      ],
      "env": {
        "DDS_API_TOKEN": "your-api-token"
      }
    }
  }
}

ツール

ツールは検出されませんでした

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

What is myCobot MCP?

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.

How to use myCobot MCP?

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.

Key features of myCobot MCP

Sends pick-and-place instructions to myCobot.
Uses DDS API for object detection.
Requires image feedback from the MCP client.
Supports configurable robot positions and speeds.
Works with suction-pump and camera-flange accessories.

Use cases of myCobot MCP

Automating pick-and-place tasks in a controlled environment.
Demonstrating MCP integration with a physical robot arm.
Teaching or prototyping robotic manipulation with visual feedback.

FAQ from myCobot MCP

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.

How do I get a DDS API token?

Does myCobot MCP require image feedback?

Yes. The server requires image feedback, so connect an MCP client that can handle image data.

What is the `settings.json` file for?

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).