universal-robot
MCP server for Universal Robots control
claude mcp add --transport stdio roversx-universal-robot-mcp uvx universal-robot-mcp
How to use
The Universal Robot MCP Server provides a standardized MCP interface to securely connect to Universal Robots hardware, monitor status, and perform precise joint and Cartesian motions. It supports real-time status queries, safe connect/disconnect workflows, and motion commands with built-in safety checks. This server is designed to be used with popular MCP clients such as Claude Desktop, the Cursor/MCP ecosystem, and VS Code MCP integrations, enabling AI assistants and other applications to reason about and direct robot actions through a consistent API.
To get started, install the server with uvx and run it, then configure your MCP client to point at the universal-robot entry. The available tools expose robot connection management, status retrieval, and motion control. For example, you can establish a connection to a UR robot, request the current joint angles and pose, or issue joint and linear motion commands with safety limits enforced by the server.
How to install
Prerequisites:
- Python 3.8+ installed on your system
- Internet access to install dependencies
- Access to a Universal Robots device or a simulation environment if testing locally
Install steps:
- Quick install (recommended):
uvx universal-robot-mcp
- Install via pip (source will fetch from PyPI):
pip install universal-robot-mcp
- Development installation (from source):
git clone https://github.com/RoversX/universal-robot-mcp
cd universal-robot-mcp
pip install -e .
- Run the server (example):
# If using uvx via the quick start
uvx universal-robot-mcp
# Or, if installed as a Python module and you want to run directly
python -m universal_robot_mcp.server
Additional notes
Tips:
- Ensure the UR robot is reachable on the network and in Remote Control mode before connecting.
- Default robot IP is typically 192.168.1.100; adjust in your environment if needed.
- The server supports simulation mode for development without hardware; enable this in your config if available.
- When integrating with AI assistants, use the provided examples to format commands for connect, status, and motion operations.
- If you encounter connection timeouts, check network routing and firewall rules between the MCP client and the UR robot.
Environment variables (if applicable):
- UR_ROBOT_IP: IP address of the UR robot
- MCP_LOG_LEVEL: logging verbosity (e.g., INFO, DEBUG)
Configuration options: The server provides safety limits for movement speed and acceleration, automatic TCP/payload configurations, and emergency stop handling. Review these defaults and adjust based on your environment and safety policies.
Related MCP Servers
packt-netops-ai-workshop
🔧 Build Intelligent Networks with AI
google-search-console
It connects directly to your Google Search Console account via the official API, letting you access key data right from AI tools like Claude Desktop or OpenAI Agents SDK and others .
Youtube
YouTube MCP Server is an AI-powered solution designed to revolutionize your YouTube experience. It empowers users to search for YouTube videos, retrieve detailed transcripts, and perform semantic searches over video content—all without relying on the official API. By integrating with a vector database, this server streamlines content discovery.
coder_db
An intelligent code memory system that leverages vector embeddings, structured databases, and knowledge graphs to store, retrieve, and analyze code patterns with semantic search capabilities, quality metrics, and relationship modeling. Designed to enhance programming workflows through contextual recall of best practices, algorithms, and solutions.
astrograph
An MCP server with tools to stop AI agents from writing duplicate code. Fixes legacy code using highly efficient algorithms.
sqllite
🗄️ SQLite MCP Server