recherche.data.gouv.fr MCP demo
by geraldineco.huggingface.geraldine/recherche-data-gouv-mcp
- Remote endpoint
- 7 tools
Uptime
Checked · every day
100%from 5 days of checks
Up without downtime on 5 of 5 days with data.
- No downtime
- Degraded
- Down over 5 minutes
- No data
- Not checked yet
Response time
Median 1201 ms, slowest 5% 1369 ms for the handshake and the tool list, over 30 days.
How far each check got
- Reached the address 100%
- Completed the handshake 100%
- Listed its tools 100%
7 tools at the last answer.
Every day
| Day | Result | Checks | Median |
|---|---|---|---|
| 3 Nov (today) | No downtime | 1 | 1260 ms |
| 2 Nov | No downtime | 1of 1 | 1246 ms |
| 1 Nov | No downtime | 1of 1 | 1287 ms |
| 31 Oct | No downtime | 1of 1 | 1279 ms |
| 30 Oct | No downtime | 1 | 1175 ms |
A failure counts as down time only when a second check five minutes later fails too. How we check
Connect to the publisher's own endpoint
Paste into Settings › Connectors › Add custom connector:
https://geraldine-recherche-data-gouv-mcp.hf.space/gradio_api/mcp/sse Run in a terminal:
claude mcp add --transport sse recherche-data-gouv-mcp https://geraldine-recherche-data-gouv-mcp.hf.space/gradio_api/mcp/sse Add to ~/.cursor/mcp.json:
Add to ~/.config/devin/mcp_config.json:
Add to mcp.json (Program › Install › Edit mcp.json):
Add to ~/.gemini/settings.json:
Add to config.json in oterm's data folder (~/Library/Application Support/oterm on macOS, ~/.local/share/oterm on Linux, %APPDATA%\oterm on Windows):
Add to ~/.config/eca/config.json (global) or .eca/config.json in the project:
{
"mcpServers": {
"recherche-data-gouv-mcp": {
"url": "https://geraldine-recherche-data-gouv-mcp.hf.space/gradio_api/mcp/sse"
}
}
} Add to .vscode/mcp.json:
{
"servers": {
"recherche-data-gouv-mcp": {
"type": "sse",
"url": "https://geraldine-recherche-data-gouv-mcp.hf.space/gradio_api/mcp/sse"
}
}
} Add to ~/.config/zed/settings.json:
{
"context_servers": {
"recherche-data-gouv-mcp": {
"url": "https://geraldine-recherche-data-gouv-mcp.hf.space/gradio_api/mcp/sse"
}
}
} This server's endpoint speaks only SSE, which this client's documentation does not list among its transports; use another client for it.
Add to cline_mcp_settings.json (MCP Servers › Configure › Configure MCP Servers):
Add to anythingllm_mcp_servers.json in the AnythingLLM storage plugins directory:
Add to Augment Settings Panel – MCP section – Import from JSON (VS Code extension):
{
"mcpServers": {
"recherche-data-gouv-mcp": {
"type": "sse",
"url": "https://geraldine-recherche-data-gouv-mcp.hf.space/gradio_api/mcp/sse"
}
}
} Add to ~/.continue/config.yaml:
mcpServers:
- name: "recherche-data-gouv-mcp"
type: sse
url: "https://geraldine-recherche-data-gouv-mcp.hf.space/gradio_api/mcp/sse" Add to ~/.config/goose/config.yaml:
extensions:
"recherche-data-gouv-mcp":
type: streamable_http
name: "recherche-data-gouv-mcp"
enabled: true
uri: "https://geraldine-recherche-data-gouv-mcp.hf.space/gradio_api/mcp/sse"
headers: {}
env_keys: []
envs: {}
timeout: 300 This server's endpoint speaks only SSE, which this client's documentation does not list among its transports; use another client for it.
Run in a terminal:
codex mcp add recherche-data-gouv-mcp --url https://geraldine-recherche-data-gouv-mcp.hf.space/gradio_api/mcp/sse This server's endpoint speaks only SSE, which this client's documentation does not list among its transports; use another client for it.
Add to ~/.llm/config.json:
Add to resources/assets/config/mcp.json in the installed app:
Add to ~/.boltai/mcp.json:
Add to ~/.bob/settings/mcp.json (global) or .bob/mcp.json (project):
Add to ~/.kiro/settings/mcp.json (user) or .kiro/settings/mcp.json (workspace):
Add to ~/.kiro/settings/mcp.json (user) or .kiro/settings/mcp.json (workspace):
{
"mcpServers": {
"recherche-data-gouv-mcp": {
"url": "https://geraldine-recherche-data-gouv-mcp.hf.space/gradio_api/mcp/sse"
}
}
} This server's endpoint speaks only SSE, which this client's documentation does not list among its transports; use another client for it.
Add to ~/.config/agenvoy/mcp.json:
{
"servers": {
"recherche-data-gouv-mcp": {
"url": "https://geraldine-recherche-data-gouv-mcp.hf.space/gradio_api/mcp/sse"
}
}
} This server's endpoint speaks only SSE, which this client's documentation does not list among its transports; use another client for it.
Add to ~/.config/amp/settings.json (user) or .amp/settings.json (workspace):
{
"amp.mcpServers": {
"recherche-data-gouv-mcp": {
"url": "https://geraldine-recherche-data-gouv-mcp.hf.space/gradio_api/mcp/sse"
}
}
} For agents: the install prompt
Every step above as one Markdown text, for an assistant installing it for you.
# Install the MCP server recherche.data.gouv.fr MCP demo (`co.huggingface.geraldine/recherche-data-gouv-mcp`)
Its page: https://plug.directory/servers/co.huggingface.geraldine/recherche-data-gouv-mcp
It runs on the publisher's servers; the client connects to its URL.
Use the section for the person's client.
## Claude Desktop
Paste into Settings › Connectors › Add custom connector:
```text
https://geraldine-recherche-data-gouv-mcp.hf.space/gradio_api/mcp/sse
```
## Claude Code
Run in a terminal:
```sh
claude mcp add --transport sse recherche-data-gouv-mcp https://geraldine-recherche-data-gouv-mcp.hf.space/gradio_api/mcp/sse
```
## Cursor, Devin Desktop, LM Studio, Gemini CLI, oterm, ECA
Merge into the place for the person's client:
- Cursor: ~/.cursor/mcp.json
- Devin Desktop: ~/.config/devin/mcp_config.json
- LM Studio: mcp.json (Program › Install › Edit mcp.json)
- Gemini CLI: ~/.gemini/settings.json
- oterm: config.json in oterm's data folder (~/Library/Application Support/oterm on macOS, ~/.local/share/oterm on Linux, %APPDATA%\oterm on Windows)
- ECA: ~/.config/eca/config.json (global) or .eca/config.json in the project
```json
{
"mcpServers": {
"recherche-data-gouv-mcp": {
"url": "https://geraldine-recherche-data-gouv-mcp.hf.space/gradio_api/mcp/sse"
}
}
}
```
## VS Code
Merge into .vscode/mcp.json:
```json
{
"servers": {
"recherche-data-gouv-mcp": {
"type": "sse",
"url": "https://geraldine-recherche-data-gouv-mcp.hf.space/gradio_api/mcp/sse"
}
}
}
```
## Zed
This server's endpoint speaks only SSE, which this client's documentation does not list among its transports; use another client for it.
## Cline, AnythingLLM, Augment Code
Merge into the place for the person's client:
- Cline: cline_mcp_settings.json (MCP Servers › Configure › Configure MCP Servers)
- AnythingLLM: anythingllm_mcp_servers.json in the AnythingLLM storage plugins directory
- Augment Code: Augment Settings Panel – MCP section – Import from JSON (VS Code extension)
```json
{
"mcpServers": {
"recherche-data-gouv-mcp": {
"type": "sse",
"url": "https://geraldine-recherche-data-gouv-mcp.hf.space/gradio_api/mcp/sse"
}
}
}
```
## Continue
Merge into ~/.continue/config.yaml:
```yaml
mcpServers:
- name: "recherche-data-gouv-mcp"
type: sse
url: "https://geraldine-recherche-data-gouv-mcp.hf.space/gradio_api/mcp/sse"
```
## Goose
This server's endpoint speaks only SSE, which this client's documentation does not list among its transports; use another client for it.
## Codex
This server's endpoint speaks only SSE, which this client's documentation does not list among its transports; use another client for it.
## mcp-client-cli, TUUI, BoltAI, Bob Shell, Kiro, Kiro CLI
This server's endpoint speaks only SSE, which this client's documentation does not list among its transports; use another client for it.
## Agenvoy
This server's endpoint speaks only SSE, which this client's documentation does not list among its transports; use another client for it.
## Amp
Merge into ~/.config/amp/settings.json (user) or .amp/settings.json (workspace):
```json
{
"amp.mcpServers": {
"recherche-data-gouv-mcp": {
"url": "https://geraldine-recherche-data-gouv-mcp.hf.space/gradio_api/mcp/sse"
}
}
}
```
Then restart the client, or reload its MCP servers, and ask it to list the server's tools to confirm it started.
Tools 7
recherche_data_gouv_mcp_get_collectionRetrieve one Recherche Data Gouv (Dataverse) collection by alias or numeric id. Returns: {"source": "recherche-data-gouv", "command": "get_collection", "identifier": str, "total_found": int | null, "returned": int, "results": [{"source": str, "type": "dataverse", "id": str, "alias": str, "name": str, "affiliation": str | null, "description": str | null, "url": str, "parent_alias": str | null, "dataset_count": int | null, "subcollection_count": int | null}], "error": str | null}recherche_data_gouv_mcp_get_datasetRetrieve the latest published version of one dataset by its persistent id. The canonical server also offers an include_raw switch that attaches the untouched upstream payload; this demo always omits it, because that payload embeds every metadata block and the whole file list. Returns: {"source": "recherche-data-gouv", "command": "get_dataset", "persistent_id": str, "total_found": int | null, "returned": int, "results": [{"source": str, "type": "dataset", "id": str, "title": str, "authors": [{"authorName": str, "authorAffiliation": str | null}], "description": str | null, "subjects": [str], "keywords": [str], "url": str, "version": str, "license": str | null, "file_count": int, "metadata_blocks": [str]}], "error": str | null}recherche_data_gouv_mcp_list_collection_contentsList the direct children of a collection: its sub-collections and its datasets. One hop down the tree, not the whole sub-tree. The upstream endpoint neither paginates nor honours a limit, so max_items clamps the answer here and total_found reports the untruncated count. Dataset entries carry a DOI but no title, and sub-collection entries a numeric id but no alias: feed either back into get_dataset or get_collection. This demo caps max_items at 25. Returns: {"source": "recherche-data-gouv", "command": "list_collection_contents", "identifier": str, "item_type": str | null, "total_found": int, "returned": int, "truncated": bool, "results": [{"source": str, "type": str, "id": str, "persistent_id": str | null, "title": str | null, "url": str | null, "publication_date": str | null}], "error": str | null}recherche_data_gouv_mcp_list_dataset_filesList the files of one dataset version, with sizes, checksums and download URLs. Like the collection listing, the upstream endpoint neither paginates nor honours a limit, so max_items clamps the answer here and total_found reports the untruncated count. This demo caps max_items at 25. download_url is the public bytes endpoint; nothing here fetches it. Returns: {"source": "recherche-data-gouv", "command": "list_dataset_files", "persistent_id": str, "version": str, "total_found": int, "returned": int, "truncated": bool, "total_size_bytes": int, "results": [{"source": str, "type": "file", "id": int, "filename": str, "content_type": str, "size_bytes": int, "restricted": bool, "download_url": str, "checksum": str | null}], "error": str | null}recherche_data_gouv_mcp_metadatablocksList the Dataverse metadata blocks of Recherche Data Gouv, or retrieve one block schema. Returns: {"source": "recherche-data-gouv", "command": "metadatablocks", "block": str | null, "data": object, "error": str | null}recherche_data_gouv_mcp_metricsFetch a public Dataverse Metrics API counter for the whole Recherche Data Gouv instance. Returns: {"source": "recherche-data-gouv", "command": "metrics", "category": str, "breakdown": str | null, "data": object, "error": str | null}recherche_data_gouv_mcp_searchSearch public Recherche Data Gouv (Dataverse) records: datasets, dataverses and files. Returns: {"source": "recherche-data-gouv", "command": "search", "query_used": str, "total_found": int, "returned": int, "results": [{"source": str, "id": str, "type": str, "title": str, "authors": [str], "url": str, "published_at": str | null}], "error": str | null}
From Hugging Face Spaces. Report a problem