Robot MCP
A simple MCP server for the SO-ARM100 control
What is Robot MCP?
Robot MCP is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to simple mcp server for the so-arm100 control
A simple MCP server for the SO-ARM100 control
This server falls under the Browser Automation category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- A simple MCP server for the SO-ARM100 control
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx robot-mcpConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Robot MCP
Robot MCP is a Python-based MCP server that provides AI assistants with direct control over the SO-ARM100 robotic arm (and partial support for the LeKiwi mobile robot). It exposes tools for checking robot status and calibration, controlling joint positions via normalized states, capturing images from attached cameras, and dispatching natural language instructions to the robot through an LLM agent — bridging conversational AI with physical robot hardware.
Prerequisites
- Python 3.10+ with pip and virtualenv
- An SO-ARM100 or SO-ARM101 robotic arm connected via USB
- The lerobot library installed (follow the official lerobot installation instructions separately)
- An API key for at least one supported LLM provider: Anthropic (ANTHROPIC_API_KEY), Google (GOOGLE_API_KEY), or OpenAI (OPENAI_API_KEY)
- Camera hardware if using image capture features
Clone the repository
Clone the robot_MCP repository to your local machine.
git clone https://github.com/IliaLarchenko/robot_MCP.git
cd robot_MCPCreate a virtual environment and install dependencies
Set up an isolated Python environment and install the required packages. The lerobot package may need to be installed separately per its own documentation.
python -m venv .venv
source .venv/bin/activate # Windows: .venv\Scripts\activate
pip install -r requirements.txtVerify robot connection and calibration
Before starting the MCP server, run the position checker script to confirm the robot is detected and calibrated correctly.
python check_positions.pyTest manual control (optional)
Use the keyboard controller to manually move the robot arm and confirm all joints respond before handing control to the AI.
python keyboard_controller.pyAdd the server to your MCP client configuration
Register the MCP server in your client's config file. Use the absolute path to the Python binary inside your venv and the absolute path to mcp_robot_server.py.
{
"mcpServers": {
"robot-mcp": {
"command": "/absolute/path/to/.venv/bin/python",
"args": ["/absolute/path/to/robot_MCP/mcp_robot_server.py"]
}
}
}Run the AI agent for natural language robot control
Use the provided agent script to send natural language instructions to the robot. Specify your preferred LLM model and optionally enable image capture for visual feedback.
python agent.py --model gemini-2.5-flash --show-imagesRobot MCP Examples
Client configuration
MCP client config for robot-mcp using a local Python venv and the mcp_robot_server.py script. Paths must be absolute.
{
"mcpServers": {
"robot-mcp": {
"command": "/home/user/robot_MCP/.venv/bin/python",
"args": ["/home/user/robot_MCP/mcp_robot_server.py"]
}
}
}Prompts to try
Natural language prompts for controlling the SO-ARM100 robot arm via the MCP tools.
- "Check the robot status and confirm all joints are calibrated"
- "Move the robot arm to the home position"
- "Capture an image from the camera and describe what you see"
- "Pick up the object in front of the robot and place it to the right"
- "Run a calibration check and report the current joint positions"Troubleshooting Robot MCP
Robot not detected — USB device not found
Check that the SO-ARM100 is connected via USB and powered on. On Linux, you may need to add your user to the 'dialout' group: 'sudo usermod -aG dialout $USER' and log out/in. On macOS, check System Information > USB for the device. Run check_positions.py to confirm detection before starting the MCP server.
lerobot import error or package not found
The lerobot library requires a separate installation process not covered by requirements.txt. Follow the official lerobot installation guide at github.com/huggingface/lerobot. Ensure you install it into the same virtual environment used by robot_MCP.
agent.py fails with API key error
Export the correct API key environment variable before running the agent: 'export ANTHROPIC_API_KEY=your_key' for Claude, 'export GOOGLE_API_KEY=your_key' for Gemini, or 'export OPENAI_API_KEY=your_key' for GPT models. The --model flag must match a model name supported by the provider whose key is set.
Frequently Asked Questions about Robot MCP
What is Robot MCP?
Robot MCP is a Model Context Protocol (MCP) server that simple mcp server for the so-arm100 control It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Robot MCP?
Follow the installation instructions on the Robot MCP GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Robot MCP?
Robot MCP works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Robot MCP free to use?
Yes, Robot MCP is open source and available under the Apache-2.0 license. You can use it freely in both personal and commercial projects.
Robot MCP Alternatives — Similar Browser Automation Servers
Looking for alternatives to Robot MCP? Here are other popular browser automation servers you can use with Claude, Cursor, and VS Code.
Chrome DevTools MCP
★ 40.6kAI-powered Chrome automation server with natural language element detection. Control Chrome browser through MCP protocol for testing, debugging, and performance analysis. Features 91% accuracy in element location, works with free AI models, and suppo
UI TARS Desktop
★ 34.9k📇 🏠 - Browser automation capabilities using Puppeteer, both support local and remote browser connection.
Playwright
★ 32.8kA production-ready browser automation server that enables AI assistants to interact with web pages using tools for navigation, element interaction, and data extraction. It features a built-in Inspector UI and robust crash recovery for reliable automa
Page Agent
★ 18.0kJavaScript in-page GUI agent. Control web interfaces with natural language.
Chrome
★ 11.7kAn extension-based MCP server that enables AI assistants to control your browser, leveraging existing sessions and login states for automation and content analysis. It provides over 20 tools for semantic tab search, interactive element manipulation,
LAMDA
★ 7.8kThe most powerful Android RPA agent framework, next generation mobile automation.
Browse More Browser Automation MCP Servers
Explore all browser automation servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Robot MCP in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Robot MCP?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.