datagouv-mcp
Official data.gouv.fr Model Context Protocol (MCP) server that allows AI chatbots to search, explore, and analyze datasets from the French national Open Data platform, directly through conversation.
Runssource: GitHubhomepagePythonMITcommit 5a37d6f0f1da
Python, MIT licensed. The project labels itself: mcp, mcp server, open data and opendata.
datagouv-mcp runs. An Argusic agent installed it in 3 minutes and hit 1 error and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
All 147 tests pass against the live data.gouv.fr API; the MCP server launches, the /health endpoint returns 200, and the MCP JSON-RPC endpoint successfully lists 9 tools and executes tool calls against the real API.
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 100 of 100 (the mean of this project's run scores).
At a glance
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.

What went wrong, in the agent's own words
The agent's own words, worst first, never rewritten into advice.
- 3 tests failed because hardcoded dataset/resource fixture IDs (55e4129788ee386899a46ec1, 3b6b2281-b9d9-4959-ae9d-c2c166dff118) no longer exist on data.gouv.fr API - returned 40410 minutes
- Install time
- 3 minutes
- Cold machine to finish
- 9 minutes
- Errors hit and fixed
- 1 hit, 1 fixed with no human help
- How the result was proved
- pytest tests/ exited 0, 147 passed (2 deselected - stress, health_check); curl -s http://localhost:8000/health returned HTTP 200 with valid JSON; curl POST to /mcp with tools/list returned all 9 tools, tools/call for search_datasets returned real results (3980 matches for 'transport')
- Model tokens used
- 66,116
- Exact commit tested
- 5a37d6f0f1da
- 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
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
exec /bin/sh -lc 'cd /work/repo && git log --oneline -5 2>&1' in /work/repo succeeded in 0ms: 5a37d6f ci: build in CI and push on new container registry (#127) Here's the final report: <pre> </pre> tokens used 66,116 Here's the final report: <pre> </pre>
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
- Reached a running state on a clean machine, with the session recorded.
- Recovered from all 1 error without a human stepping in, which says the failures are documented well enough to solve.
- Ran without a GPU, so it does not need one to start.
- Licensed MIT, as reported by its host.
- Measured 2 times, so the result is not a one-off.
What did not, or is not known
- Took 3 minutes to install, slower than the median of the 15 comparable projects Argusic has measured.
Of the 16 mcp projects Argusic has installed and timed, datagouv-mcp was the 12th fastest to reach a running state, and 14 of 16 reached one at all.
What it is a reasonable choice for
- Trying it on a laptop or a small server: it reached a running state without a GPU.
- A quick evaluation: it was running 3 minutes after the clone.
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
Topics (from GitHub)
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/datagouv-mcp)Questions
- Does datagouv-mcp run?
- Yes. datagouv-mcp runs. Argusic installed and launched it on a clean machine in 3 minutes, hitting 1 error on the way, and recorded the session.
- How did Argusic test datagouv-mcp?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 5a37d6f0f1da. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test datagouv-mcp?
- The run that produced this verdict cost $0.04: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does datagouv-mcp take to install?
- 3 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 datagouv-mcp need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing datagouv-mcp?
- 1 thing broke in the recorded run, and 1 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does datagouv-mcp compare with the alternatives?
- Of the 16 mcp projects Argusic has installed and timed, datagouv-mcp was the 12th fastest to reach a running state, and 14 of 16 reached one at all.
- Where is the evidence for datagouv-mcp?
- All 2 recorded runs are on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.