Robot MCP Server
Enables LLM-based AI agents to control SO-ARM100 and SO-101 robots through natural language commands and camera feedback. It supports various transport protocols and provides tools for both autonomous robotic movement and manual keyboard operation.
What is Robot MCP Server?
Robot MCP Server is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to enables llm-based ai agents to control so-arm100 and so-101 robots through natural language commands and camera feedback. it supports various transport protocols and provides tools for both autonomous...
Enables LLM-based AI agents to control SO-ARM100 and SO-101 robots through natural language commands and camera feedback. It supports various transport protocols and provides tools for both autonomous robotic movement and manual keyboard operation.
This server falls under the Browser Automation category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Enables LLM-based AI agents to control SO-ARM100 and SO-101
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx robot-mcp-serverConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Robot MCP Server
Robot MCP Server enables LLM-based AI agents to control SO-ARM100 and SO-101 robotic arms through natural language commands by exposing robot control capabilities as MCP tools. It supports multiple transport protocols and integrates with major LLMs (Claude, Gemini, GPT) to enable fully autonomous robotic movement guided by camera feedback and visual verification. Beyond full AI control, it also supports manual keyboard operation, making it a flexible platform for both research and production robotic workflows.
Prerequisites
- Python 3.x with pip and venv support
- SO-ARM100, SO-101, or LeKiwi robot hardware connected via USB or network
- At least one LLM API key: ANTHROPIC_API_KEY, GEMINI_API_KEY, or OPENAI_API_KEY
- Camera(s) connected and recognized by the operating system
- An MCP-compatible client such as Claude Desktop, Cursor, or Windsurf
Clone the repository
Clone the robot_MCP repository to your machine.
git clone https://github.com/IliaLarchenko/robot_MCP
cd robot_MCPCreate a virtual environment and install dependencies
Isolate the project dependencies in a virtual environment and install from requirements.txt.
python -m venv .venv
source .venv/bin/activate # Windows: .venv\Scripts\activate
pip install -r requirements.txtConfigure robot connection and cameras
Edit config.py to set the serial port or IP address for your robot and the camera indices or names. This file controls motor calibration mappings as well.
Create the .env file with API keys
Create a .env file in the project root with your LLM API key(s) and optional server settings.
ANTHROPIC_API_KEY=your-anthropic-key
GEMINI_API_KEY=your-gemini-key
OPENAI_API_KEY=your-openai-key
MCP_SERVER_IP=127.0.0.1
MCP_PORT=3001Verify robot connection
Run the position check script to confirm the robot is detected and motors respond correctly before starting the MCP server.
python check_positions.pyStart the MCP server
Launch the robot MCP server using SSE transport so MCP clients can connect and send natural language robot commands.
mcp run mcp_robot_server.py --transport sseRun the AI agent directly (alternative)
Instead of an MCP client, you can run the included agent script that drives the robot autonomously using your chosen LLM.
python agent.py --model gemini-2.5-flash --show-images --thinking-budget 2048Robot MCP Server Examples
Client configuration
Claude Desktop configuration for the Robot MCP server using SSE transport on localhost.
{
"mcpServers": {
"robot-mcp": {
"url": "http://127.0.0.1:3001/sse",
"env": {
"ANTHROPIC_API_KEY": "your-anthropic-key"
}
}
}
}Prompts to try
Once connected, send natural language commands to control the robotic arm.
- "Move the robot arm to the home position."
- "Pick up the object in front of the camera and place it to the left."
- "Take a camera snapshot and describe what you see on the workspace."
- "Rotate the wrist joint 45 degrees clockwise."
- "Perform a calibration check on all motors and report their current positions."Troubleshooting Robot MCP Server
Robot not detected on the configured serial port
Run 'ls /dev/tty.*' (macOS) or 'ls /dev/ttyUSB*' (Linux) to find the correct port. Update the port value in config.py. On Windows, check Device Manager for the COM port number.
Camera feed not working or returning black frames
Verify camera indices in config.py by testing with a simple OpenCV script: 'cv2.VideoCapture(0)'. Try index 0, 1, 2 in sequence. On macOS, ensure camera permissions are granted to the Python process in System Settings.
High LLM token costs during autonomous operation
Each vision-based decision loop sends camera images to the LLM, which can be expensive. Use the --thinking-budget flag to limit reasoning tokens and reduce --show-images polling frequency. Consider using Gemini Flash for lower per-token costs during development.
Frequently Asked Questions about Robot MCP Server
What is Robot MCP Server?
Robot MCP Server is a Model Context Protocol (MCP) server that enables llm-based ai agents to control so-arm100 and so-101 robots through natural language commands and camera feedback. it supports various transport protocols and provides tools for both autonomous robotic movement and manual keyboard operation. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Robot MCP Server?
Follow the installation instructions on the Robot MCP Server GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Robot MCP Server?
Robot MCP Server works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Robot MCP Server free to use?
Yes, Robot MCP Server is open source and available under the Apache 2.0 license. You can use it freely in both personal and commercial projects.
Robot MCP Server Alternatives — Similar Browser Automation Servers
Looking for alternatives to Robot MCP Server? 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 Server 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 Server?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.