ros2-mcp-server

Created By
MCP-Mirrora year ago
Mirror of
Overview

What is ros2-mcp-server?

ros2-mcp-server is a Python-based server that integrates the Model Context Protocol (MCP) with ROS 2, allowing AI assistants to control robots via ROS 2 topics. It processes commands through FastMCP and operates as a ROS 2 node, publishing movement commands to control robot actions.

How to use ros2-mcp-server?

To use the server, clone the repository, set up the environment with Python 3.10, install dependencies, and configure it as an MCP server for clients like Claude or Cline. Once configured, you can send commands to control the robot's movement.

Key features of ros2-mcp-server?

  • MCP Integration: Handles commands from MCP clients using FastMCP.
  • ROS 2 Native: Operates as a ROS 2 node, publishing to the /cmd_vel topic.
  • Time-Based Control: Supports commands for movement duration.
  • Asynchronous Processing: Efficiently combines FastMCP's asyncio with ROS 2's event loop.

Use cases of ros2-mcp-server?

  1. Controlling robots in simulations like Gazebo.
  2. Integrating AI assistants to automate robot movements.
  3. Testing movement commands in real-world robotic applications.

FAQ from ros2-mcp-server?

  • Can I use this server with any robot?

Yes, as long as the robot subscribes to the /cmd_vel topic.

  • What are the prerequisites for using this server?

You need ROS 2 Humble, Python 3.10, and specific dependencies like FastMCP and numpy.

  • How do I troubleshoot connection issues?

Ensure the MCP server configuration is correct and all dependencies are installed.

Project Info
Created At
a year ago
Updated At
a year ago
Author Name
MCP-Mirror
Star
0
Language
Python
License
-

Recommend Servers

View All
Tavily Mcp
@tavily-ai

JavaScript
a year ago
AI Work Market — USDC settlement rails for AI labor on Base Mainnet)
@Dario (DME)

AI Work Market is a USDC escrow protocol on Base Mainnet, designed for autonomous AI agents to find work, post jobs, and settle payments without humans in the loop. This MCP server exposes 10 tools: **Escrow lifecycle** - `create_intent_quote` — get calldata + gas estimate for funding a new escrow intent - `submit_proof_quote` — get calldata for the seller to submit a proof URI - `release_funds_quote` — get calldata for the buyer to release payment (or claim/refund) **x402 single-call binding** - `x402_consume` — replaces the 5-step x402 flow with one HMAC-signed POST that returns a delivery URL **Onboarding & discovery** - `agent_onboard` — generate a signed agent card with marketplace attestation - `agent_search` — tf-idf search over the live agent catalog - `agent_reputation` — server-side reputation from on-chain Released/Refunded/Disputed events **Live state** - `system_status` — live on-chain state (nextIntentId, accumulatedFees, contract balance, owner) - `escrow_rules` — contract semantics, lifecycle, call guides, failure modes - `events_subscribe` — SSE stream of new on-chain intent events All endpoints are serverless (Vercel) and return their schema on GET. No browser, no wallet UI required for an agent to integrate. The protocol takes a 1% commission on every settlement; the rest goes to the seller. The full AgentCard is at `/.well-known/agent-card.json` (A2A-compatible). The OpenAPI 3.0.3 spec is at `/.well-known/openapi.json` with `components.securitySchemes` (none, hmacX402). `robots.txt` allows GPTBot, ClaudeBot, anthropic-ai, PerplexityBot, Google-Extended, Applebot-Extended, CCBot, Amazonbot.

42 minutes ago