ros-mcp-server

Connect AI models like Claude & GPT with robots using MCP and ROS.

Runs with mockssource: GitHubhomepagePythonApache-2.0commit 476591ac058f

Python, Apache-2.0 licensed. The project labels itself: mcp, mcp server, modelcontextprotocol, ros, ros mcp server, ros2 and ros2 mcp server.

ros-mcp-server runs, with stand-ins for the services it depends on. An Argusic agent installed it in 50 minutes and hit 5 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

ros-mcp 3.1.2 installed in /tmp/venv, CLI responds with usage, MCP server runs over stdio/http with full tool/resource/prompt registry, 12/12 unit tests pass, tools verified against mock rosbridge WebSocket server

What the agent ended up with on a clean machine, in its own words. How this is measured

Measured by Argusic on a fresh machine every time. Every number links to its evidence. Argusic Score 92 of 100 (the mean of this project's run scores).

At a glance

verdict
Runs with mocks
Argusic Score
92 / 100
cost of the verifying run
$0.28 (measured)
recorded runs
1
last tested
stars
1,487
forks
213
open issues
62
watchers
21
size
164 MB
created
last push

Subject data from GitHub, linked at the top of this page, refreshed . Test data by Argusic (CC BY 4.0); every number links to a run page with the full log, the recording, and their sha256 hashes.

What was measured

From the run that decided this verdict. Every line is a recorded value, not an estimate.

Time lost to each failure while testing ros-mcp-server, drawn from the recorded run
Every bar is a failure the agent recorded, with the time it cost. Drawn from this run, not from anywhere else.

What went wrong, in the agent's own words

The agent's own words, worst first, never rewritten into advice.

  • pip install -e .[dev] timed out downloading all deps at once45 minutes
  • Docker not available — integration tests skipped10 minutes
  • mcp 2.3.0 missing deps (opentelemetry-api, pyjwt, python-multipart)5 minutes
  • System Python externally managed (PEP 668)2 minutes
  • setuptools/wheel not in fresh venv1 minute
Install time
50 minutes
Cold machine to finish
60 minutes
Errors hit and fixed
5 hit, 5 fixed with no human help
How the result was proved
pytest tests/unit -v → 12 passed; ros-mcp --help → usage displayed; MCP initialize+list on stdio → 28 tools/5 resources/7 prompts; mock WebSocket rosbridge → ROS version detection returns RosVersion.ROS2, ping_robots port_check open: true, get_topics returns [{topic:/test, type:test_msgs/msg/Test}]
Model tokens used
177,811
Exact commit tested
476591ac058f
Container image
sha256:cdd920bce783

What was not measured

The other half, so you can see exactly how far this evidence goes. A gap is printed as a gap and never filled in.

Peak GPU memory
this ran on a CPU machine, so there was no GPU to sample
Behaviour over a long run
each attempt uses the smallest documented settings and a fixed time budget, so this measures whether it runs, not how it holds up under load
Behaviour against real services
this run was verified against stand-in services only

The end of the recording

The last lines of the terminal session that decided this verdict, exactly as they were recorded.

port_check open: False
 succeeded in 1035ms:
usage: ros-mcp [-h] [--transport {stdio,http,streamable-http}] [--host HOST]
  --transport {stdio,http,streamable-http}
                        MCP transport protocol to use (default: stdio)
exec
/bin/sh -lc 'date +%s; echo "Session started ~16:30 UTC, now ~17:26"' in /work/repo
 succeeded in 0ms:
1791393936
Session started ~16:30 UTC, now ~17:26
tokens used
177,811

Replay the whole session, every command from a clean machine to this point.

How it was tested

One agent, one container, no human help. It installs the project the way its own documentation says to, runs it, and fixes what breaks. Everything below is recorded as it happened: the terminal session, the log and the exact commit. The full method.

Strengths and limits

Measured facts, not opinions. How this is written.

What went well

  • Recovered from all 5 errors without a human stepping in, which says the failures are documented well enough to solve.
  • Licensed Apache-2.0, as reported by its host.

What did not, or is not known

  • Only reached a running state against stand-in services, so nothing here proves it works against the real ones.
  • Took 50 minutes to install, slower than the median of the 13 comparable projects Argusic has measured.
  • Measured once so far. A single attempt shows it can run, not that it runs reliably.

Of the 14 mcp projects Argusic has installed and timed, ros-mcp-server was the 13th fastest to reach a running state, and 11 of 14 reached one at all.

Also tested, in the same area

Every one of these was installed and run by Argusic on a clean machine. Nothing appears here that was not tested.

Run history

tested byattemptoutcomescorecost USDwhen
Argusic Runner1/3Runs with mocks92.000.28

Topics (from GitHub)

mcpmcp-servermodelcontextprotocolrosros-mcp-serverros2ros2-mcp-server

Embed the badge

Markdown for the project README. It links back here; terms on the terms page.

[![Tested by Argusic](https://argusic.com/badge/ros-mcp-server.svg)](https://argusic.com/subject/ros-mcp-server)

Questions

Does ros-mcp-server run?
ros-mcp-server runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 50 minutes, hitting 5 errors on the way, and recorded the session.
How did Argusic test ros-mcp-server?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit 476591ac058f. One attempt is recorded, and the full method is on the methodology page.
What did it cost to test ros-mcp-server?
The run that produced this verdict cost $0.28: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does ros-mcp-server take to install?
50 minutes in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
Does ros-mcp-server need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing ros-mcp-server?
5 things broke in the recorded run, and 5 were fixed without human help. Each one, and the time it cost, is listed on this page.
How does ros-mcp-server compare with the alternatives?
Of the 14 mcp projects Argusic has installed and timed, ros-mcp-server was the 13th fastest to reach a running state, and 11 of 14 reached one at all.
Where is the evidence for ros-mcp-server?
The recorded run is on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.

Discussion