What is ros-mcp AGENTS.md?

Repository instructions for a ROS MCP server, including its command-line tools, code layout, motion rules, and simulator topics. ROS is software for building robot applications, and an MCP server exposes those robot controls to compatible AI clients.

Use it when running, configuring, extending, or testing the ROS MCP server and its tools for topics, services, nodes, and simulated turtle robots.

It gives contributors the project-specific rules needed to add tools safely and avoid incorrect robot commands. In particular, it documents which operations can change motion and how simulated robots are addressed.

How jonasneves/ros-mcp configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to jonasneves/ros-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/jonasneves/ros-mcp/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/jonasneves/ros-mcp

Made for: Codex, OpenCode.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/jonasneves/ros-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/jonasneves/ros-mcp/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/jonasneves/ros-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/jonasneves/ros-mcp/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/jonasneves/ros-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/jonasneves/ros-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,019 This file is loaded in full into every session.

When invoked 1,019 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.01019	$0.01019
Opus 5.5	$0.00408	$0.00408
Sonnet 5.5	$0.00204	$0.00204
Haiku 4.5	$0.00102	$0.00102

Measured 5d ago against content hash 2cc45a27c4ef, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ros-mcp AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

AGENTS.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ROS MCP Server

Commands

Run server: uv run server.py
Add to Claude (local): make configure

Architecture

Tools are registered in src/ros_mcp/tools/ and wired up in src/ros_mcp/server.py. Each tool file owns one domain (topics, services, nodes, etc.). New tools go in the relevant file and must be registered in server.py.

Tool conventions

readOnlyHint=True for read-only tools, destructiveHint=True for anything that publishes or mutates state
Tool descriptions must include units and a concrete example call
Motion tools must send a zero-velocity stop command as their last action
Use turn_by_angle / move_by_distance for rotation and straight-line motion — do not use publish_for_durations for these; it requires the caller to compute duration = angle_rad / angular_velocity and is error-prone

Simulator cmd_vel topics

The bundled setup runs 3 namespaced turtlesim instances (ts1, ts2, ts3):

Instance	Topic	Message type
turtlesim1	`/ts1/turtle1/cmd_vel`	`geometry_msgs/Twist`
turtlesim2	`/ts2/turtle1/cmd_vel`	`geometry_msgs/Twist`
turtlesim3	`/ts3/turtle1/cmd_vel`	`geometry_msgs/Twist`

Docker / DDS networking

All containers must use the same DDS middleware. The rosbridge container requires RMW_IMPLEMENTATION=rmw_cyclonedds_cpp in docker-compose.yml — without it, rosbridge defaults to FastDDS and cannot discover topics from the simulator containers (which use CycloneDDS via entrypoint.sh).

cyclonedds.xml is baked into images via COPY, so changes require docker compose build before --force-recreate.

Isaac Sim

Isaac Sim uses FastDDS (ROS 2 default). The turtlesim setup forces CycloneDDS on rosbridge — do not reuse that compose file for Isaac Sim.

docker/docker-compose.isaac-sim.yml starts rosbridge with:

network_mode: host — sees Isaac Sim DDS multicast
No RMW_IMPLEMENTATION — falls back to FastDDS, matching Isaac Sim

Read the full file on GitHub · 65 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

5d ago Changed · -1 lines · -36 tokens per session 2cc45a27c4ef
1mo ago First seen · 66 lines · 1,055 tokens per session scan A a6d1080220cb

Subscribe to this mod's changes

ros-mcp AGENTS.md is an instructions file published in the GitHub repository jonasneves/ros-mcp (3 stars, last pushed 6d ago), licensed Apache-2.0. It adds 1,019 tokens to every session, about $0.0041 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-19.

Building agents Hardware and IoT Python mcp model-context-protocol robotics ros ros2

ros-mcp AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
ros-mcp AGENTS.mdjonasneves/ros-mcp	Instructions file	3	6d ago	Apache-2.0	A	1,019	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

ros-mcp: Instructions file for Codex