mcp-data-gouv-fr
# mcp-data-gouv-fr
MCP server for searching and inspecting French public datasets on data.gouv.fr.
## Scope
French open-data discovery, datasets, resources, organizations, and public API catalog navigation.
## Tools
- `data_gouv_fr_get_sources`
- `data_gouv_fr_search_data_gouv`
- `data_gouv_fr_get_dataset`
- `data_gouv_fr_fetch_source_excerpt`
- `data_gouv_fr_explain_scope`
- `data_gouv_fr_list_reference_items`
- `data_gouv_fr_search_organizations`
- `data_gouv_fr_search_dataservices`
- `data_gouv_fr_list_dataset_resources`
- `data_gouv_fr_preview_resource`
## Install
```bash
npm install
npm run build
npm test
npm run dev
```
## Claude Desktop
```json
{
"mcpServers": {
"data-gouv-fr": {
"command": "npx",
"args": ["mcp-data-gouv-fr"]
}
}
}
```
## Sources
- data.gouv.fr API reference: https://doc.data.gouv.fr/api/reference/
- data.gouv.fr dataset API guide: https://guides.data.gouv.fr/api-de-data.gouv.fr/reference/datasets
- data.gouv.fr public API catalog: https://www.data.gouv.fr/dataservices
- data.gouv.fr explorer: https://explore.data.gouv.fr/
## Example Prompts
- "Search for datasets about air quality in France."
- "Find resources for a data.gouv.fr dataset slug."
- "List public API catalog entries related to transport."
## Safety
This MCP helps agents discover and summarize public sources. It is not an official authority. For emergency, legal, or administrative decisions, follow the competent public service.
## Glama / Docker
The repo includes `Dockerfile` and `glama.json`.
Publishing notes: [`docs/publishing.md`](docs/publishing.md).
Build steps:
```json
["npm install", "npm run build"]
```
CMD arguments:
```json
["node", "dist/index.js"]
```
## License
MIT
TDQS
Scored across 9 tools
Tools target distinct resources (sources, datasets, organizations, dataservices, vocabulary). However, 'get_sources' and 'fetch_source_excerpt' both relate to curated sources, requiring a clear two-step workflow, and 'explain_scope'/'list_reference_items' are meta/utility tools that might overlap in edge cases. Overall, clear separation of purpose is evident.
All tools follow a consistent pattern: 'data_gouv_fr_' prefix plus a verb-noun or verb-object structure (get_sources, search_data_gouv, get_dataset, fetch_source_excerpt, list_reference_items). Minor deviation: 'explain_scope' is a meta-utility rather than a data operation, but naming remains predictable.
9 tools for this server's scope (discovering and exploring data.gouv.fr resources) is reasonable and well-balanced. It's not too sparse nor overloaded. The inclusion of utility tools like 'explain_scope' and 'list_reference_items' slightly widens scope, but overall count is appropriate.
Covers discovery (search datasets, organizations, dataservices), inspection (get_dataset, list resources), and curated source access (get_sources, fetch_source_excerpt). Minor gap: no direct download or full text fetch of a resource (only excerpt), and no tool to browse dataset metadata beyond basic inspection, but core workflows are present.