ros-mcp-server
Connect large language models with robots for bidirectional communication.
- Type
- MCP
- Transport
- stdio
- Open source
- Yes
- GitHub Stars
- ★ 1.3k
- Source
- mcp-github
- Repository
- github.com/robotmcp/ros-mcp-server
Overview
ROS-MCP-Server enables bidirectional communication between large language models (such as Claude, GPT, and Gemini) and robots. No need to modify existing robot source code—just add a `rosbridge` node. This capability allows LLMs to control and observe robots, publish and subscribe to topics, call services and actions, set parameters, read sensor data, and monitor robot status in real time. Compatible with any MCP client and supports both ROS 1 and ROS 2 versions.
Capabilities
- ▪Bidirectional communication
- ▪No modification of robot source code required
- ▪Publish and subscribe to topics
- ▪Call services and actions
- ▪Set parameters
- ▪Read sensor data
Use cases
Setup
Please refer to the [installation guide](docs/install/installation.md) to get started.
This information was compiled by AI from public sources and may contain inaccuracies — please refer to the source.
FAQ
Which versions of ROS are supported?
Supports multiple versions of ROS 1 and ROS 2.
Do I need to modify existing robot code?
No, you only need to add the `rosbridge` node.
Related skills
pstack-claude
Provides rigorous workflows for multiple agents, supporting Claude Code, Codex, and more.
sast-skills
Transform your AI coding assistant into a SAST scanner to automatically detect vulnerabilities in code.
Lightswind-UI-Library
AI-native CLI-first React component library with MCP Server support.
scientific-agent-skills
Transform any AI agent into a scientific assistant with 147 ready-to-use research skills.
susi_alexa_skill
A skill that enables question-and-answer interactions between Alexa and Susi AI.
claude-context
Provides code search capabilities for Claude Code, turning the entire codebase into context.