ROS MCP Server
The ROS MCP Server translates natural language commands into ROS/ROS2 robot commands via WebSocket communication, enabling seamless interaction with robotic systems.
Publish Twist Messages: Control robot movement by publishing linear and angular velocity commands.
Sequential Commands: Execute a sequence of movements with specified durations.
Cross-Platform Compatibility: Operates on Linux, Windows, and MacOS.
AI Integration: Directly translates natural language inputs from LLMs/AI systems into robot actions.
Extensible Functionality: Easily add new control or sensor functions.
No Code Modifications: Works with existing ROS/ROS2 topics and services without changing robot code.
Message Support: Handles various message types including
geometry_msgs/Twist,sensor_msgs/Image, andsensor_msgs/JointState.Simulation Tested: Verified with MOCA mobile manipulator in NVIDIA Isaac Sim.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@ROS MCP Server move forward at 0.5 m/s and turn left slowly"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
ROS MCP Server 🧠⇄🤖
ROS-MCP-Server connects large language models (such as Claude, GPT, and Gemini) to robots, enabling bidirectional communication with no changes to existing robot source code.
Why ROS-MCP?
No robot source code changes → just add the
rosbridgenode to your existing ROS setup.True two-way communication → LLMs can both control robots and observe everything happening on the Robot.
Full context → publish & subscribe to topics, call services & actions, set parameters, read sensor data, and monitor robot state in real time.
Deep ROS understanding → guides the LLM to discover available topics, services, actions, and their types (including custom ones) — enabling it to use them with the right syntax without manual configuration.
Works with any MCP client → built on the open MCP standard, supporting Claude Code, Codex CLI, Gemini CLI, Claude Desktop, ChatGPT, Cursor, and more.
Works across ROS versions → compatible across ROS 2 (Jazzy, Humble, and others) and ROS 1 distros.
🎥 Examples in Action
🏭 Example - AI Agent diagnosis of Industrial Robot End Effector (Video)
The MCP server connects Claude to a production industrial robot, with only the technician manuals as reference.
Claude discovers the robot's custom topic and service types and their syntax on its own.
From a single prompt to test the gripper, it reads the manuals, runs its own tests, finds an anomaly, and reports the root cause.
🤖 Example - Controlling "Wilson" with natural language (video)
From a single prompt — "Grab a Coke from the fridge & go to the living room." — Google Gemini uses the MCP server to navigate and manipulate autonomously. Built on ROS 2 with Nav2 (SLAM) for mapping and navigation, and MoveIt to command the manipulator.
🐕 Example - Controlling Unitree Go2 in NVIDIA Isaac Sim (video)
The MCP server connects Claude to a simulated Unitree Go2 quadruped in NVIDIA Isaac Sim, interpreting natural language commands to navigate and control the robot.
Related MCP server: ROS MCP Server
🛠 Getting Started
Follow the installation guide to get started.
ROS-MCP works with Claude Code, Codex CLI, Gemini CLI, Claude Desktop, ChatGPT, Cursor, or any MCP-compatible client.
📚 More Examples & Tutorials
Browse our examples to see the server in action.
We welcome community PRs with new examples and integrations!
🤝 Contributing
We love contributions of all kinds:
Bug fixes and documentation updates
New features (e.g., Action support, permissions)
Additional examples and tutorials
Check out the contributing guidelines and see issues tagged good first issue to get started.
📜 License
This project is licensed under the Apache License 2.0.
Available Tools
17 toolscall_serviceC
Call a ROS service with specified request data. Example: call_service('/rosapi/topics', 'rosapi/Topics', {})
Inputs: request (required), service_name (required), service_type (required).
get_message_detailsB
Get the complete structure/definition of a message type. Example: get_message_details('geometry_msgs/Twist')
Inputs: message_type (required).
get_publishers_for_topicC
Get list of nodes that are publishing to a specific topic. Example: get_publishers_for_topic('/cmd_vel')
Inputs: topic (required).
get_service_detailsC
Get complete service details including request and response structures. Example: get_service_details('my_package/CustomService')
Inputs: service_type (required).
get_service_providersC
Get list of nodes that provide a specific service. Example: get_service_providers('/rosapi/topics')
Inputs: service (required).
get_servicesB
Get list of all available ROS services. Example: get_services()
Inputs: no named parameters.
get_service_typeC
Get the service type for a specific service. Example: get_service_type('/rosapi/topics')
Inputs: service (required).
get_subscribers_for_topicC
Get list of nodes that are subscribed to a specific topic. Example: get_subscribers_for_topic('/cmd_vel')
Inputs: topic (required).
get_topicsC
Fetch available topics from the ROS bridge. Example: get_topics()
Inputs: no named parameters.
get_topic_typeC
Get the message type for a specific topic. Example: get_topic_type('/cmd_vel')
Inputs: topic (required).
inspect_all_servicesB
Get comprehensive information about all services including types and providers. Example: inspect_all_services()
Inputs: no named parameters.
ping_robotA
Ping a robot's IP address and check if a specific port is open. A successful ping to the IP but not the port can indicate that ROSbridge is not running. Example: ping_robot(ip='192.168.1.100', port=9090)
Inputs: ip (required), port (required), ping_timeout, port_timeout.
publish_for_durationsC
Publish a sequence of messages with delays. Example: publish_for_durations(topic='/cmd_vel', msg_type='geometry_msgs/msg/TwistStamped', messages=[{'linear': {'x': 1.0}}, {'linear': {'x': 0.0}}], durations=[1, 2])
Inputs: durations, messages, msg_type, topic.
publish_onceC
Publish a single message to a ROS topic. Example: publish_once(topic='/cmd_vel', msg_type='geometry_msgs/msg/TwistStamped', msg={'linear': {'x': 1.0}})
Inputs: msg, msg_type, topic.
set_websocket_ipC
Set the IP and port for the WebSocket connection.
Inputs: ip (required), local_ip (required), port (required).
subscribe_for_durationB
Subscribe to a topic for a duration and collect messages. Example: subscribe_for_duration(topic='/cmd_vel', msg_type='geometry_msgs/msg/TwistStamped', duration=5, max_messages=10)
Inputs: duration, max_messages, msg_type, topic.
subscribe_onceA
Subscribe to a ROS topic and return the first message received. Example: subscribe_once(topic='/cmd_vel', msg_type='geometry_msgs/msg/TwistStamped')
Inputs: msg_type, topic.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 17 tools
Most tools have distinct purposes focused on different ROS operations like service calls, topic management, and network configuration. However, there is some overlap between get_services and inspect_all_services, as well as between subscribe_once and subscribe_for_duration, which could cause minor confusion in tool selection.
The naming follows a consistent snake_case pattern with clear verb_noun structures like get_topics, call_service, and publish_once. Minor deviations exist, such as ping_robot (which is more specific) and set_websocket_ip (which uses 'set' instead of a more common verb like 'configure'), but overall the conventions are readable and predictable.
With 17 tools, the count is slightly high but reasonable for a ROS server that needs to cover services, topics, messages, and network operations. It provides comprehensive functionality without being overwhelmingly large, though it borders on the upper limit of a well-scoped set.
The tool set offers complete coverage for ROS operations, including CRUD-like actions for services and topics (e.g., call, get, publish, subscribe), message and service details retrieval, and network configuration tools. There are no obvious gaps, and agents can handle core workflows like monitoring, publishing, and service interaction effectively.
Maintenance
Related MCP Connectors
Zero-auth ROS 2 Humanoid, Q3 Proxemics, 3-Level Voice Arbiter, A2A-MCP Bridge & W3C VC 2.0.
Connect Claude, Cursor, Codex, and other AI tools to your robotics mission data.
Operate Linux, macOS and Windows from your LLM. Every action runs through an auditable allowlist.
Drive real Android & iOS devices and web browsers from natural language for mobile + web QA. 290+ tools across device control, app management, automation sessions, browser automation, and flow recording / replay. Bearer-auth — get a token at robotactions.com → Profile → API Tokens.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceA Python-based server that enables AI assistants to control robots by integrating the Model Context Protocol (MCP) with ROS 2, allowing for natural language commands that translate into robot movement via the /cmd\_vel topic.84-
- AlicenseNot gradedqualityDmaintenanceEnables control of ROS/ROS2 robots through natural language commands by translating LLM instructions into ROS topics and services. Supports cross-platform WebSocket-based communication with existing robot systems without requiring code modifications.MIT
- AlicenseNot gradedqualityDmaintenanceEnables robot navigation control and monitoring through natural language. Provides tools for robot positioning, navigation to coordinates, device status monitoring, task management, and emergency controls.MIT
- FlicenseNot gradedqualityDmaintenanceEnables LLMs to control a two-track robot through movement commands, providing independent track control, high-level directional driving (forward, backward, left, right), and emergency stop functionality.-