Atlas Scolaire
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., "@Atlas ScolaireCompare the bac results of Lycée Louis-le-Grand and Lycée Henri-IV, including their IPS and value-added."
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.
Atlas Scolaire — MCP server
2025 brevet and baccalauréat results for the 10,098 collèges and lycées of France métropolitaine, served to AI assistants over the Model Context Protocol — with one rule built into every response: a school's success index never travels without its social intake (IPS), the intake's spread, and the ministry's value-added. Read alone, the success index measures who a school admits more than what it does.
The data comes from atlas-scolaire.fr, which joins six open datasets — five published by the French education ministry, plus the Base adresse nationale — under Licence Ouverte 2.0.
Connect
Endpoint:
https://mcp.atlas-scolaire.fr/mcp(Streamable HTTP, no authentication)Claude.ai / Claude Desktop: Settings → Connectors → Add custom connector, then paste the endpoint.
Claude Code:
claude mcp add --transport http atlas-scolaire https://mcp.atlas-scolaire.fr/mcp
Related MCP server: mcp-french-school-map
Tools
Tool | What it returns |
| Identities only (UAI, name, commune, page): many schools share a name. |
| One school, results (each with its national percentile) with intake and value-added. |
| 2–5 schools in the order given, no computed winner. |
| A commune or département, 25 per page ( |
| Schools near an address or a point, nearest first by default, 25 per page; |
| Schools of the same type with a comparable IPS, nearest first, up to 10. |
| Area aggregates, each result median paired with its median IPS. |
A response that holds several schools states the reading note (how_to_read) and the
attribution once, at its top level; get_school carries both on its single record.
Plus two resources (atlas://methodology, atlas://sources) and one prompt
(choose_a_school).
Lists can be ordered by results, as the site's own tables are, one exam at a time: a
list ordered by success index or value-added gives each school its rank among the
schools ranked on the same exam (ranked_on) — ranks restart for each exam, and no rank
compares a brevet with a bac, or one bac with another — and every exam carries the
school's national success_index_percentile. What never happens is a
result travelling alone: every ranked school carries its IPS, the IPS standard
deviation and its value-added in the same record.
Evaluation
A pilot comparing four conditions (no tools, web, web + a naive server with the same data, web + this server) is written up in evals/RESULTS.md, with the plan in evals/PLAN.md.
Data and licence
Data: /donnees/etablissements.v1.json,
Licence Ouverte 2.0 — the six sources are listed at
atlas-scolaire.fr/#sources. Code: MIT.
Development
npm install
npm test # unit tests over a hand-built fixture: no data file, no network
LIVE=1 npm test # also downloads and indexes the live data file
npm run check # tsc
npm run fetch-data # download the data file into data/ (git-ignored)
npm run dev # fetch-data, then wrangler dev on http://localhost:8787/mcp
npm run deploy # fetch-data, then wrangler deployThe data file is not fetched at request time: npm run fetch-data downloads it, checks
its version, and wrangler bundles it into the Worker, which builds its index once at
start-up. A data refresh on the site therefore reaches this server only through a
redeploy — npm run deploy downloads the current file first.
This server cannot be deployed
Maintenance
Related MCP Connectors
California school data for AI agents — scores, profiles, comparisons, feeder paths, UC pipelines.
13 pay-per-event data APIs for local-business and web intelligence: local presence audit (Google Business Profile + reviews + AI-readiness), Google Maps scraper, review radar and review pitch generator, TikTok, Instagram, YouTube and LinkedIn scrapers, RAG web browser, France fuel prices, hotel rate monitoring, and a free AEO/AI visibility checker.
French address intelligence: 18.6M sold prices, energy, risk, crime and schools — each sourced.
Live SEO intelligence, rank tracking, site audits, and backlink analysis for AI agents.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceEnables AI assistants to query and validate BNCC (Brazilian curriculum) skills deterministically, preventing hallucinations by providing official data, search, and code validation tools.-
- AlicenseBqualityBmaintenanceEnables discovery and summarization of French education data, including school directories, geocoded establishments, IPS, Parcoursup, and exam datasets.5MIT
- AlicenseNot gradedqualityCmaintenanceEnables AI assistants to search and retrieve French job profiles, RNCP certifications, training programs, training centers, and skills comparisons in read-only mode without requiring an account.MIT
- FlicenseNot gradedqualityBmaintenanceConnects AI agents to the École Directe API to access grades, homework, timetables, school life, messages, and documents.-