ros2-mcp
Provides tools to read ROS2 topics, call services, get robot status and GPS telemetry, and wrap telemetry into verifiable ai2robot proof bundles. Supports both mock (simulated) and real ROS2 modes via a Python sidecar.
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., "@ros2-mcp List the robot topics and show the current GPS position."
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.
ros2-mcp
ROS2 ↔ MCP bridge: let any AI agent (Claude Code, OpenClaw, Cursor) read ROS2 topics, call services, and wrap telemetry into verifiable proof bundles.
Two modes:
Mock mode (default) — simulated robot, zero ROS2 required. Try it now.
ROS2 mode — real topics/services via a Python sidecar (
rclpy).
Quick start (mock, 2 minutes)
npm install
npm run build
npm startRegister with your agent:
claude mcp add ros2-mcp -- npx tsx src/index.tsThen ask:
"List the robot topics, then tell me the current GPS position." "Move the robot forward, then wrap the telemetry into a proof bundle for task task_ros2_001."
Related MCP server: ROS 2 MCP Server
Tools
Tool | Purpose |
| list ROS2 topics |
| latest value of a topic |
| call a service (e.g. |
| status + GPS + telemetry in one call |
| wrap telemetry into an ai2robot proof bundle draft (hash-chained) |
| genesis hash for a task |
Real ROS2
Requires a ROS2 environment (tested pattern: ros:humble docker image):
docker run -it --rm ros:humble
apt-get install -y python3-pip && pip install rclpy # usually preinstalledThen run the server with the sidecar:
AI2ROBOT_ROS2=1 npm startThe sidecar (python/ros2_bridge.py) subscribes to all topics generically and
exposes them over stdio JSON-lines. It is a reference implementation; bring
your own transport if you need typed QoS or specific vendors.
Why proof mode
wrap_proof emits bundles in the
ai2robot proof format
(hash-chained action log + GPS traces; Ed25519 signature added by the
executor's key). Any fleet using this bridge can become an ai2robot executor
without changing hardware — the bridge is the adapter kernel.
License
MIT
Available Tools
6 toolscall_serviceB
Call a ROS2 service (e.g. cmd_vel to move the robot).
Inputs: service (required), args.
chain_fingerprintA
Return the SHA-256 fingerprint of the proof draft for a task.
Inputs: taskId (required).
list_topicsA
List available ROS2 topics.
Inputs: no named parameters.
read_topicB
Read the latest value of a ROS2 topic.
Inputs: topic (required).
robot_statusA
Convenience: read status, GPS and telemetry in one call.
Inputs: no named parameters.
wrap_proofC
Wrap current robot telemetry into an ai2robot proof bundle draft (hash-chained action log).
Inputs: events (required), taskId (required), executorId (required), escrowId.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 6 tools
Each tool targets a distinct aspect of the robot: listing topics, reading from a topic, invoking a service, aggregated status, proof bundle creation, and fingerprint hashing. There is no meaningful overlap that would cause misselection.
Most tools follow a verb_noun pattern (list_topics, read_topic, call_service, wrap_proof), but robot_status and chain_fingerprint are noun phrases, creating a minor deviation. The pattern is still readable and mostly predictable.
Six tools is well-scoped for a ROS2 interface that covers topic access, service calls, telemetry aggregation, and proof generation. The count feels appropriate for the apparent purpose without bloat or thinness.
Core functionality like reading topics and calling services is present, but there are notable gaps: no way to publish to topics, no service discovery or type introspection, and no node listing. The proof tools are an extra feature but do not compensate for missing standard ROS2 operations.
Maintenance
Related MCP Connectors
Tamper-evident proof creation and verification for AI agents via MCP, A2A, and REST.
MCP server for your apps' tools and custom tools, plus hosted AI agents and approval-gated workflows
MCP server for AI agents to plan, verify, and deploy Cloudflare-native apps.
MCP server for the Z1N Protocol - on-chain identity for AI agents on Polygon
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 gradedqualityDmaintenanceA Model Context Protocol server for ROS 2, enabling AI assistants to introspect and interact with ROS 2 systems.26 PyPI2MIT
- AlicenseNot gradedqualityCmaintenanceMCP server for AI agents to inspect and control ROS2 graphs, enabling topic listing, node info, service calls, parameter management, and pub/echo without manual ROS2 CLI usage.12MIT
- AlicenseAqualityDmaintenanceA Model Context Protocol (MCP) server for ROS 2 that enables GitHub Copilot and other AI agents to interact with ROS 2 systems. This server provides tools for monitoring, debugging, and managing ROS 2 nodes, topics, services, and TF2 frames.1534 npmMIT