# robotmcp/ros-mcp-server

Connect AI models like Claude & GPT with robots using MCP and ROS.

Repository: https://github.com/robotmcp/ros-mcp-server
Canonical: https://ross.abutalabs.com/products/ros-mcp-server
Homepage: https://robotmcp.ai
Language: Python
License: Apache-2.0
License Family: permissive
Topics: ros, ros2, ros-mcp-server, ros2-mcp-server, mcp, mcp-server, modelcontextprotocol
Last push: 2026-08-26T08:31:12+00:00

## Health v2 (maintenance only)
Score: 83/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 89, longevity 36
- inputs: {"age_days": 509, "days_push": 7, "days_rel": 77, "gap_med": 6.5, "n_releases_24m": 13}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1413, forks 209 (observed 2026-08-28T04:04:39.469991+00:00)

## What it is
A Model Context Protocol (MCP) server that connects LLMs like Claude, GPT, and Gemini to robots via ROS and ROS 2, using rosbridge for bidirectional communication without modifying robot source code. It lets AI models discover topics, services, and actions, then control and monitor robots through natural language.

## Use cases
- control a robot with natural language via Claude or GPT
- connect LLMs to ROS 2 robots over MCP
- let an AI agent diagnose and debug an industrial robot
- monitor robot sensor topics from a chat interface
- command a drone or quadruped with a single prompt
- integrate AI assistants with existing ROS setups without code changes

## When to choose
- you have a ROS or ROS 2 robot and want LLM-based control or monitoring
- you want MCP-standard integration with Claude, ChatGPT, Gemini, or other MCP clients
- you need two-way communication (publish, subscribe, services, actions) with no robot code changes

## When to avoid
- your robot does not use ROS or rosbridge
- you need hard real-time or safety-critical control without an LLM in the loop
- you cannot run a Python 3.10+ server near the robot or expose a tunnel

## Facets
- artifact type: service
- maturity: active
- function: mcp, robotics, agent-framework, middleware
- domain: robotics, large-language-models
- platform: python, self-hosted
- tags: ros, ros2, rosbridge, mcp-server, llm-robot-control, natural-language-robotics, ai-agents, automation, linux, docker

## Member repositories
- robotmcp/ros-mcp-server (main) score 83

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:39.469991+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:38:17.575067+00:00, confidence not recorded.
  - readme: https://github.com/robotmcp/ros-mcp-server (fetched 2026-08-28T04:04:39.469991+00:00, sha 883bd540a28f)
  - homepage: https://robotmcp.ai (fetched 2026-08-29T11:51:23.993285+00:00, sha 7b4cf81018ea)
  - site_page: https://robotmcp.ai/getting-started (fetched 2026-08-29T11:51:24.002215+00:00, sha a787679b1fbf)
- Data as of 2026-08-30T08:39:29.467469+00:00.