robot_MCP

Name: robot_MCP
Rating: 2.1 (78 reviews)
Author: IliaLarchenko

by IliaLarchenko·★ 78·Score 42

MCP server for controlling SO-ARM100 robots through LLM agents with manual keyboard control option.

ai-llmdeveloper-toolsother

Forks

Open issues

9 mo ago

Last commit

2d ago

Indexed

Overview

robot_MCP is a Python-based MCP server that enables AI agents to control SO-ARM100/101 robots through the Model Context Protocol. It provides both LLM-based control and manual keyboard operation, with support for Claude, Gemini, and GPT models. The server implements multiple transport protocols including stdio, SSE, and streamable-HTTP, making it compatible with various MCP clients like Claude Desktop, Cursor, and Windsurf.

Try asking AI

After installing, here are 5 things you can ask your AI assistant:

you:Enabling AI agents to control robots through natural language commands

you:Providing manual robot control via keyboard interface

you:Creating multimodal AI applications with robot vision capabilities

you:Which robot models are supported?

you:What are the supported LLM models?

When to choose this

Choose this MCP server if you need to control SO-ARM100 or LeKiwi robots through AI agents with natural language instructions, and especially if you're already using Claude or Gemini models.

When NOT to choose this

Avoid this server if you need support for other robot models, require more recent updates (last commit was 9 months ago), or need a more production-ready solution with long-term maintenance guarantees.

Tools this server exposes

2 tools extracted from the README (low confidence)

check_positions
Check robot status and calibration without actual control
keyboard_control
Control the robot manually using keyboard

Note: No explicit tool documentation found. Tool names inferred from CLI commands in the README (check_positions.py and keyboard_controller.py). The actual MCP tools exposed by mcp_robot_server.py are not documented in the README.

Comparable tools

lerobotpyrobotros-mcpmcp-server

Installation

Create and activate a virtual environment:

python -m venv .venv
source .venv/bin/activate  # or .venv\Scripts\activate on Windows

Install dependencies:

pip install -r requirements.txt

Update config.py with your robot connection parameters

For Claude Desktop, add to your configuration:

{
  "mcpServers": {
    "SO-ARM100 robot controller": {
      "command": "/path/to/.venv/bin/python",
      "args": ["/path/to/mcp_robot_server.py"]
    }
  }
}

FAQ

Which robot models are supported?: Currently supports SO-ARM100/101 and partially supports LeKiwi (only arm control, mobile base control through MCP is planned).
What are the supported LLM models?: Supports Claude (Anthropic), Gemini (Google), and GPT (OpenAI) models, though the author reports best results with Claude and suboptimal results with GPT.

Compare robot_MCP with

robot_MCP vs ultimate_mcp_server robot_MCP vs mcp-server-chart robot_MCP vs everything robot_MCP vs filesystem robot_MCP vs time

GitHub →

Last updated 2026-05-17 · Auto-generated from public README + GitHub signals.