/ Verzeichnis / Playground / data.gouv.fr
● Offiziell datagouv ⚡ Sofort

data.gouv.fr

von datagouv · datagouv/datagouv-mcp

Search and query French government open-data datasets on data.gouv.fr — no API key, instant access to thousands of public datasets.

France's official open-data MCP exposes the data.gouv.fr catalog: full-text search over datasets and organizations, metadata retrieval, resource downloads. Useful for French civic-tech research, journalism, and policy analysis without paying or registering.

Warum nutzen

Hauptfunktionen

Live-Demo

In der Praxis

datagouv.replay ▶ bereit
0/0

Installieren

Wählen Sie Ihren Client

~/Library/Application Support/Claude/claude_desktop_config.json  · Windows: %APPDATA%\Claude\claude_desktop_config.json
{
  "mcpServers": {
    "datagouv": {
      "command": "uvx",
      "args": [
        "datagouv-mcp"
      ]
    }
  }
}

Öffne Claude Desktop → Settings → Developer → Edit Config. Nach dem Speichern neu starten.

~/.cursor/mcp.json · .cursor/mcp.json
{
  "mcpServers": {
    "datagouv": {
      "command": "uvx",
      "args": [
        "datagouv-mcp"
      ]
    }
  }
}

Cursor nutzt das gleiche mcpServers-Schema wie Claude Desktop. Projektkonfiguration schlägt die globale.

VS Code → Cline → MCP Servers → Edit
{
  "mcpServers": {
    "datagouv": {
      "command": "uvx",
      "args": [
        "datagouv-mcp"
      ]
    }
  }
}

Klicken Sie auf das MCP-Servers-Symbol in der Cline-Seitenleiste, dann "Edit Configuration".

~/.codeium/windsurf/mcp_config.json
{
  "mcpServers": {
    "datagouv": {
      "command": "uvx",
      "args": [
        "datagouv-mcp"
      ]
    }
  }
}

Gleiche Struktur wie Claude Desktop. Windsurf neu starten zum Übernehmen.

~/.continue/config.json
{
  "mcpServers": [
    {
      "name": "datagouv",
      "command": "uvx",
      "args": [
        "datagouv-mcp"
      ]
    }
  ]
}

Continue nutzt ein Array von Serverobjekten statt einer Map.

~/.config/zed/settings.json
{
  "context_servers": {
    "datagouv": {
      "command": {
        "path": "uvx",
        "args": [
          "datagouv-mcp"
        ]
      }
    }
  }
}

In context_servers hinzufügen. Zed lädt beim Speichern neu.

claude mcp add datagouv -- uvx datagouv-mcp

Einzeiler. Prüfen mit claude mcp list. Entfernen mit claude mcp remove.

Anwendungsfälle

Praxisnahe Nutzung: data.gouv.fr

Find a French public dataset by topic

👤 Journalists, researchers, civic-tech devs ⏱ ~10 min beginner

Wann einsetzen: You need 'unemployment by département, monthly' or similar and don't know where it lives.

Ablauf
  1. Search by keywords
    Search data.gouv.fr for 'chômage département mensuel'. Return top 10 datasets with title, publisher, last update.✓ Kopiert
    → Relevant dataset list
  2. Inspect the most promising
    For the top 3, fetch full metadata: license, update frequency, resources, description. Which is the most current + official?✓ Kopiert
    → Comparison summary
  3. Get download URLs
    Return the CSV resource URL(s) for the chosen dataset. I'll download it separately.✓ Kopiert
    → Direct download URL(s)

Ergebnis: A shortlist of authoritative datasets with direct download links.

Fallstricke
  • Datasets sometimes have broken resource URLs — Check the 'last_modified' metadata; older + unmaintained = more likely broken. Prefer INSEE-published if available.
Kombinieren mit: filesystem

Catalog all datasets published by a specific ministry or agency

👤 Researchers mapping data availability ⏱ ~15 min intermediate

Wann einsetzen: You want to know everything INSEE or Ministère de la Transition écologique publishes.

Ablauf
  1. Look up the organization
    Find the data.gouv organization page for 'INSEE'. Return its slug.✓ Kopiert
    → Canonical org id
  2. List all datasets
    List every dataset published by that org. Page through all results. Return title, id, last update, resource count.✓ Kopiert
    → Full catalog
  3. Categorize
    Group by theme (population, economy, territory, etc.). Count datasets per theme.✓ Kopiert
    → Thematic histogram

Ergebnis: A structured inventory of a French public org's open data.

Fallstricke
  • Large orgs have 1000+ datasets — pagination matters — Always page through all results; don't trust the first page as complete
Kombinieren mit: filesystem

Watch for newly published or updated datasets on a topic

👤 Civic tech / policy analysts ⏱ ~15 min intermediate

Wann einsetzen: You want to be alerted when new COVID/election/housing datasets appear.

Ablauf
  1. Baseline search today
    Search for '<topic>' and save the top 50 dataset ids + last_modified dates as /data/datagouv-<topic>-baseline.json.✓ Kopiert
    → Baseline saved
  2. Weekly rerun
    Rerun the search. Compare against baseline. Return (a) new datasets not in baseline, (b) datasets whose last_modified increased.✓ Kopiert
    → Delta report
  3. Surface the interesting ones
    Filter the delta by official publishers (ministries, INSEE, agencies). Produce a 1-line summary per new/updated dataset.✓ Kopiert
    → Curated digest

Ergebnis: A weekly alert on authoritative new French data in your topic.

Fallstricke
  • Aggregators re-publish old data with new last_modified — noise — Prefer datasets whose publisher is an official org, not a re-publishing community
Kombinieren mit: filesystem

Kombinationen

Mit anderen MCPs für 10-fache Wirkung

datagouv + filesystem

Download and archive datasets locally

Search 'recensement population' on data.gouv, pick the INSEE one, download CSV, save to /data/insee/.✓ Kopiert
datagouv + postgres

Ingest a French open dataset into Postgres for analysis

Download the latest unemployment dataset, infer schema, CREATE TABLE and COPY into Postgres.✓ Kopiert
datagouv + antv-chart

Quick chart from a French open dataset

Download dataset X, filter to 2020-2024, render as a line chart per région.✓ Kopiert

Werkzeuge

Was dieses MCP bereitstellt

WerkzeugEingabenWann aufrufenKosten
search_datasets q: str, page?, page_size? Keyword search over datasets free
get_dataset dataset_id_or_slug Full metadata + resources for a specific dataset free
search_organizations q: str Find a ministry/agency's canonical id free
list_organization_datasets org_id, page? Catalog a publisher's full output free

Kosten & Limits

Was der Betrieb kostet

API-Kontingent
Public API; fair-use throttling (few req/sec is safe)
Tokens pro Aufruf
Dataset metadata: 500–2000 tokens depending on field count
Kosten in €
Free
Tipp
Cache dataset ids locally; metadata rarely changes week-over-week.

Sicherheit

Rechte, Secrets, Reichweite

Credential-Speicherung: None needed
Datenabfluss: All calls to www.data.gouv.fr and resource hosts

Fehlerbehebung

Häufige Fehler und Lösungen

404 on get_dataset

Dataset id changed or was delisted. Use search instead of a cached id.

Rate limited

Space out calls; <5 req/sec is safe. No official limit but fair-use enforced.

Resource URL returns 403/404

Some datasets have broken links; prefer the most recently updated resource or the official publisher's own page.

Alternativen

data.gouv.fr vs. andere

AlternativeWann stattdessenKompromiss
data.europa.eu MCPYou need pan-EU data, not just FranceBroader but less French-specific depth
INSEE API MCPYou only need official INSEE stats with clean API accessNarrower scope; French statistical office only

Mehr

Ressourcen

📖 Offizielle README auf GitHub lesen

🐙 Offene Issues ansehen

🔍 Alle 400+ MCP-Server und Skills durchsuchen