PluginBench
MCP Server
Active
MPL-2.0

io.github.wise-vision/mcp_server_ros_2 MCP Server

io.github.wise-vision/mcp_server_ros_2

Connect AI agents to ROS 2 nodes, topics, services, and actions via Model Context Protocol.

RepositoryRegistry

What is the io.github.wise-vision/mcp_server_ros_2 MCP server?

The ROS 2 MCP Server is a Python implementation of the Model Context Protocol that enables AI tooling to interact with ROS 2 systems over stdio. It provides tools to list, subscribe to, and publish messages on topics; call services; and send/monitor action goals, with automatic type discovery and QoS selection.

This server bridges ROS 2 robotics systems with AI agents like Claude and Cursor, allowing natural language control and debugging of robots. Use it to query sensor data, call services, monitor topics, manage actions, and troubleshoot ROS 2 issues without requiring deep ROS expertise. Designed for 1-minute setup with zero external dependencies.

How to install io.github.wise-vision/mcp_server_ros_2

Copy-paste configuration for popular MCP clients.

transport: stdio
Config generated by PluginBench — verify against the source before use.
Environment / auth
  • MCP_CUSTOM_PROMPTS

    Enable custom prompts

  • MCP_PROMPTS_LOCAL

    Use local prompts

  • MCP_PROMPTS_PATH

    Path to custom prompts directory

  • MCP_PROMPTS_MODULE

    Name of the prompts module

~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "mcp_server_ros_2": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "docker.io/mcp/ros2:latest",
        "-v",
        "~/mcp_custom_messages:/app/custom_msgs"
      ],
      "env": {
        "MCP_CUSTOM_PROMPTS": "<YOUR_MCP_CUSTOM_PROMPTS>",
        "MCP_PROMPTS_LOCAL": "<YOUR_MCP_PROMPTS_LOCAL>",
        "MCP_PROMPTS_PATH": "<YOUR_MCP_PROMPTS_PATH>",
        "MCP_PROMPTS_MODULE": "<YOUR_MCP_PROMPTS_MODULE>"
      }
    }
  }
}

Tools & capabilities

Tools this server exposes to the agent.

  • ros2_topic_list — Returns list of available topics with their message types
  • ros2_topic_subscribe — Subscribes to a ROS 2 topic and collects messages for a specified duration or message limit
  • ros2_topic_publish — Publishes a message to a ROS 2 topic
  • ros2_get_message_fields — Gets field names and types for a message type
  • ros2_get_messages — Retrieves past messages from a topic via WiseVision Data Black Box
  • ros2_service_list — Returns list of available services with their types and request fields
  • ros2_service_call — Calls a ROS 2 service with specified parameters
  • ros2_list_actions — Returns list of available ROS 2 actions with their types and request fields
  • ros2_send_action_goal — Sends a goal to an action and optionally waits for the result
  • ros2_action_request_result — Waits for the result of a given action goal
  • ros2_action_subscribe_feedback — Subscribes to feedback messages from an action goal
  • ros2_action_subscribe_status — Subscribes to status updates from an action
  • ros2_cancel_action_goal — Cancels a specific action goal or all active goals

Use cases

  • Monitor robot sensor data in real-time and analyze message rates and statistics
  • Control robot actions and services through natural language commands without ROS expertise
  • Debug ROS 2 systems by comparing topics, checking node health, and verifying synchronization
  • Retrieve historical sensor data from the data black box for analysis and post-processing
  • Relay and transform messages between topics with optional rate limiting and filtering

io.github.wise-vision/mcp_server_ros_2 MCP server FAQ

What is the ROS 2 MCP Server?

It's a Python MCP server that connects AI agents (Claude, Cursor) to ROS 2 systems, enabling topic pub/sub, service calls, action management, and automatic type discovery over stdio transport.

Is it free?

Yes, the ROS 2 MCP Server is open-source and free to use. It's available on GitHub and as a Docker image.

How do I install it in Claude Desktop?

Follow the installation guide at https://github.com/wise-vision/mcp_server_ros_2/blob/main/installation/README.md#configure-claude-desktop for step-by-step instructions.

How do I install it in Cursor?

Cursor uses the same MCP configuration as Claude Desktop. See the installation guide for detailed setup steps.

Do I need ROS 2 expertise to use it?

No. The server auto-discovers message types and provides AI-powered assistance, so you can control robots and debug issues through natural language without deep ROS knowledge.

Does it require authentication or external services?

No. It uses stdio transport with zero external brokers or webservers. It can optionally integrate with WiseVision Data Black Box (InfluxDB) for historical data, but that's optional.

README (reference)

Source of truth, from the repository.

ROS2 MCP Server

Discord ROS 2 Humble ROS 2 Jazzy Docker GitHub stars

Flow graph

A Python implementation of the Model Context Protocol (MCP) for ROS 2. This server enables AI tooling to connect with ROS 2 nodes, topics, and services using the MCP standard over stdio. Designed to be the easiest ROS 2 MCP server to configure.

✨ Tools

  • List available topics
  • List available services
  • Lists available actions with their types and request fields
  • Call services
  • Subscribe to topics to collect messages
  • Publish messages to topics
  • Echo messages on topics
  • Get fields from message types
  • Sends an action goal and optionally waits for the result
  • Requests the result of an action goal
  • Subscribes to feedback messages from an action
  • Subscribes to status updates of an action
  • Cancels a specific goal or all active goals
  • Get messages from WiseVision Data Black Box (InfluxDB alternative to Rosbag2)

🤖 Available Prompts

📘 Want to create a custom prompt? Check the guide here

📊 base.ros2-topic-echo-and-analyze

Subscribe to a ROS2 topic, collect messages for a specified duration, and provide statistical analysis of the collected data.

➡️ Can auto-detect topic if only one is available. Analyzes message rates, counts, and statistics on numeric fields.

🔄 base.ros2-topic-relay

Subscribe to one ROS2 topic and republish messages to another topic with optional transformations.

➡️ Supports identity relay, rate limiting, and change-based filtering.

🏥 base.ros2-node-health-check

Check if expected ROS2 topics and services are available and functioning correctly with optional publication rate monitoring.

➡️ Provides comprehensive health report with status indicators and recommendations.

🔍 base.ros2-topic-diff-monitor

Compare two ROS2 topics and report differences in their messages with detailed field-by-field analysis.

➡️ Useful for comparing raw sensor data with filtered/processed versions or verifying topic synchronization.

ROS2 MCP has Prompts extension with additional prompts See here

💡 Don’t know what prompts are? See the MCP spec here.

Note: To call a service with a custom (non-default) type, source the package that defines it before starting the server.

🎯 Why Choose This MCP Server?

Save hours of development time with native AI integration for your ROS 2 projects:

Why this ROS 2 MCP server ⭐

  • ⚡ 1-minute setup - World's easiest ROS 2 MCP configuration
  • 0️⃣ Zero-friction setup - stdio transport, no brokers, no webserver.
  • 🔌 Auto type discovery - a built-in “list interfaces” tool dynamically enumerates available topics and services together with their message/service definitions (fields, types, schema) — so the client always knows exactly what data can be published or called.
  • ✨ Nested field support: Handle complex message structures with ease.
  • 🤖 AI-powered debugging - Let AI help you troubleshoot ROS 2 issues in real time
  • 📊 Smart data analysis - Query your robot's sensor data using natural language
  • 🚀 Boost productivity - Control robots, analyze logs, and debug issues through AI chat
  • 💡 No ROS 2 expertise required - AI translates your requests into proper ROS 2 commands
  • 🐋 Dockerized: Ready-to-use Docker image for quick deployment.
  • 🔧 Auto QoS selection: Automatically selects appropriate Quality of Service settings for topics and services, ensuring optimal communication performance without manual configuration.

Perfect for: Robotics developers, researchers, students, and anyone working with ROS 2 who wants to leverage AI for faster development and debugging.

If you find this useful, please ⭐ star the repo — it helps others discover it.

🚀 Enjoying this project? Feel free to contribute or reach out for support! Write issues, submit PRs, or join our Discord community to connect with other ROS 2 and AI enthusiasts.

🤝 Contributing

Contributions are welcome! Please check the open issues for ways to help, open a pull request, or drop by our Discord to discuss ideas before diving in. By participating, you agree to follow our Code of Conduct.

🚀 Drone Mission Using Prompts

Drone mission demo

🌍 Real-world examples:

Demo

⚙️ Installation

Follow the installation guide for step-by-step instructions:

🧭 DDS discovery warm-up (Docker)

If the first tool call returns an incomplete list of topics/services right after container start, DDS discovery may still be in progress. The server performs a one-time warm-up on the first tool call in container environments; tune it via:

  • MCP_ROS_DISCOVERY_STABLE_SEC (default: 1.0)
  • MCP_ROS_DISCOVERY_TIMEOUT_SEC (default: 5.0)
  • MCP_ROS_DISCOVERY_WARMUP=false to disable

💡 Want to try it in simulation?

Check out the Gazebo Drone Demo section

🔧 ROS 2 Tools

📋 Topics

ToolDescriptionInputsOutputs
ros2_topic_listReturns list of available topics–topic_name (string): Topic name <br> topic_type (string): Message type
ros2_topic_subscribeSubscribes to a ROS 2 topic and collects messages for a duration or message limittopic_name (string) <br> duration (float) <br> message_limit (int) <br> (defaults: first msg, 5s)messages <br> count <br> duration
ros2_get_messagesRetrieves past messages from a topic (data black box)topic_name (string) <br> message_type (string) <br> number_of_messages (int) <br> time_start (str) <br> time_end (str)timestamps <br> messages
ros2_get_message_fieldsGets field names and types for a message typemessage_type (string)Field names + types
ros2_topic_publishPublishes message to a topictopic_name (string) <br> message_type (string) <br> data (dict)status

🛠 Services

ToolDescriptionInputsOutputs
ros2_service_listReturns list of available services–service_name (string) <br> service_type (string) <br> request_fields (array)
ros2_service_callCalls a ROS 2 serviceservice_name (string) <br> service_type (string) <br> fields (array) <br> force_call (bool, default: false)result (string) <br> error (string, if any)

🎯 Actions

ToolDescriptionInputsOutputs
ros2_list_actionsReturns list of available ROS 2 actions with their types and request fields–actions[] (array) <br> └ name (string) <br> └ types[] (array of string) <br> └ request_fields (array)
ros2_send_action_goalSends a goal to an action. Optionally waits for the result.action_name (string) <br> action_type (string) <br> goal_fields (object) <br> wait_for_result (bool, default: false) <br> timeout_sec (number, default: 60.0)accepted (bool) <br> goal_id (string|null) <br> send_goal_stamp (object|null) <br> waited (bool) <br> result_timeout_sec (number|null) <br> status_code (int|null) <br> status (string|null) <br> result (object|null) | error (string)
ros2_cancel_action_goalCancels a specific goal or all goals for an actionaction_name (string) <br> goal_id_hex (string, required if cancel_all=false) <br> cancel_all (bool, default: false) <br> stamp_sec (int, default: 0) <br> stamp_nanosec (int, default: 0) <br> wait_timeout_sec (number, default: 3.0)service (string) <br> return_code (int) <br> return_code_text (string) <br> goals_canceling[] (array of {goal_id, stamp}) | error (string)
ros2_action_request_resultWaits for the RESULT of a given goal via GetResultaction_name (string) <br> action_type (string) <br> goal_id_hex (string, 32-char UUID) <br> timeout_sec (number|null, default: 60.0) <br> wait_for_service_sec (number, default: 3.0)service (string) <br> goal_id (string) <br> waited (bool) <br> result_timeout_sec (number|null) <br> status_code (int|null) <br> status (string|null) <br> result (object|null) | error (string)
ros2_action_subscribe_feedbackSubscribes to feedback messages for an action. Can filter by goal_id. Collects messages for duration or max count.action_name (string) <br> action_type (string) <br> goal_id_hex (string|null) <br> duration_sec (number, default: 5.0) <br> max_messages (int, default: 100)topic (string) <br> action_type (string) <br> goal_id_filter (string|null) <br> duration_sec (number) <br> messages[] (array of {goal_id, feedback, recv_stamp}) | error (string)
ros2_action_subscribe_statusSubscribes to an action's status topic and returns collected status framesaction_name (string) <br> duration_sec (number, default: 5.0) <br> max_messages (int, default: 100)topic (string) <br> duration_sec (number) <br> frames[] (array of {stamp, statuses[]}) | error (string)

🐞 Debugging

Since MCP servers run over stdio, debugging can be challenging. For the best debugging experience, we strongly recommend using the MCP Inspector.

You can launch the MCP Inspector via npm with this command:

npx @modelcontextprotocol/inspector uv --directory /path/to/ros2_mcp run mcp_ros_2_server

Upon launching, the Inspector will display a URL that you can access in your browser to begin debugging.

📚 Origins and evolution

We built this server to make AI‑assisted ROS 2 development fast and reliable. Internally, we needed a simple way for agents to discover message types, publish/subscribe to topics, and call services—without boilerplate or flaky networking. That led to a few core design goals:

  • Handle all ROS 2 message types (including nested fields) so agents can write and test any code
  • Integrate topic pub/sub and service calls to validate behavior end‑to‑end
  • Work seamlessly with GitHub Copilot in VS Code and other MCP clients
  • Use a simple stdio transport to avoid network complexity

After dogfooding it, we open‑sourced the project to help the broader ROS 2 community build faster with AI. It’s now useful not only for development, but also for controlling robots, running QoS experiments, and analyzing live data and robot/swarm state. The project is actively maintained—features and improvements ship regularly based on user feedback. If this project helps you, please star the repo and share your use case!

Related MCP servers

IOio.github.wiseappsai/play-console-mcp logo

io.github.wiseappsai/play-console-mcp

Manage Google Play Console: releases, listings, monetization, reviews, and Android Vitals.

View repository →
AIAION SUPREME Agent Temple logo

AION SUPREME Agent Temple

Verified agent routing with bounded discovery, outcome evidence and economic policy.

View repository →
IOio.github.wiserautomation/suprawall-mcp logo

io.github.wiserautomation/suprawall-mcp

Maintained

SupraWall security gateway for AI agents. Provides deterministic guardrails for MCP agents.

2
TypeScript
Apache-2.0
View repository →
IOio.github.wishfinity/wishfinity-mcp-plusw logo

io.github.wishfinity/wishfinity-mcp-plusw

Maintained

Save any product URL to your Wishfinity wishlist. Works with any MCP client.

1
TypeScript
MIT
View repository →
WIWistia API logo

Wistia API

Manage Wistia videos, channels, folders, captions, customizations, and analytics via MCP.

IOio.github.with-geun/alive-analysis logo

io.github.with-geun/alive-analysis

Maintained

Structured analysis workflow for AI agents — every analysis traceable, repeatable, and team-shareable.

41
HTML
MIT
View repository →