# Data Nantes [Health: Active]

**Category:** 📊 Data Platforms  
**Repository:** https://github.com/pipeworx-io/mcp-data-nantes  
**GitHub Stars:** 0  
**npm Downloads (last month):** 430  
**Views:** 2  
**Installs:** 0  
**Upvotes:** 0  
**Directory Page:** https://allmcps.com/mcp/data-nantes

## Description
Nantes Métropole Open Data (data.nantesmetropole.fr) — OpenDataSoft MCP.

## Tools
Capabilities this server exposes over MCP:

- **search_datasets** — Search Nantes Métropole Open Data for datasets by keyword (mobility, urban services, environment & geography). Returns dataset_ids (pass to query/dataset_info), titles, themes and record counts.
- **dataset_info** — Get metadata for one Nantes Métropole Open Data dataset (fields/schema, themes, record count) — call before query to learn the column names.
- **query** — Query records from a Nantes Métropole Open Data dataset with ODSQL. Filter (where), aggregate (group_by/select), sort (order_by), paginate (limit/offset).

## Claude Desktop Quick Installation
Install path detected from listing signals. Uses `npx` (confidence: high):

```json
"mcpServers": {
  "data-nantes": {
    "command": "npx",
    "args": ["-y","@pipeworx/mcp-data-nantes"]
  }
}
```

## Documentation

## What Data Nantes does

Data Nantes provides MCP access to Nantes Métropole Open Data, the OpenDataSoft-based public data service at data.nantesmetropole.fr. It is suited to questions involving datasets such as mobility, urban services, environment, and geography.

The server exposes three dataset-focused tools:

- `search_datasets` finds datasets by keyword and returns identifiers, titles, themes, and record counts.
- `dataset_info` returns metadata for a selected dataset, including its fields, schema, themes, and record count.
- `query` retrieves dataset records using ODSQL options for filtering, aggregation, sorting, and pagination.

The integration is independent and unofficial; it is not published, endorsed, or affiliated with the upstream data provider.

## How it works

A typical workflow starts with `search_datasets`, using a term such as mobility or transport. Pass a returned dataset ID to `dataset_info` to learn the available column names before constructing a query. Use `query` to select records and apply a `where` filter, `group_by` and `select` expressions, `order_by`, or `limit` and `offset` pagination.

The hosted MCP endpoint is available at `https://gateway.pipeworx.io/data-nantes/mcp`. That endpoint lists the three Data Nantes tools along with shared Pipeworx gateway tools. The gateway also provides `ask_pipeworx`, which can route a natural-language request to the appropriate tool across the broader catalog.

For direct access to only the Data Nantes tools, run the package as a local stdio MCP server. The local and hosted options use the same source and expose the same pack-specific tools, while the hosted connection includes the gateway's shared tools.

## Setup and configuration

Add the hosted endpoint to an MCP client with a remote server configuration:

```json
{
  "mcpServers": {
    "data-nantes": {
      "url": "https://gateway.pipeworx.io/data-nantes/mcp"
    }
  }
}
```

The package can also be launched locally through `npx`:

```json
{
  "mcpServers": {
    "data-nantes": {
      "command": "npx",
      "args": ["-y", "@pipeworx/mcp-data-nantes"]
    }
  }
}
```

The local process communicates over stdin and stdout and does not require a Pipeworx account. The hosted gateway can also be called over HTTP; for example, the dataset search tool is available through the corresponding `/v1/tools/data_nantes_search_datasets` endpoint.

## Tools and capabilities

### `search_datasets`

Searches Nantes Métropole Open Data by keyword. Results include dataset IDs for subsequent calls, along with titles, themes, and record counts.

### `dataset_info`

Inspects one dataset's metadata, including its schema and field names. Use it before writing a query when the available columns are unknown.

### `query`

Runs an ODSQL query against a dataset. Supported operations include record filtering with `where`, aggregation through `group_by` and `select`, sorting with `order_by`, and result pagination using `limit` and `offset`.

## Limitations and notes

The hosted pack endpoint includes shared Pipeworx meta-tools in addition to the three Data Nantes tools, so its tool list is larger than the local server's list. The exact gateway scope can vary and is reported by the connection's `initialize` response.

The local server exposes only the Data Nantes pack tools and does not provide `ask_pipeworx` or other shared gateway tools. Both deployment modes target the Nantes Métropole Open Data source; the main difference is whether requests use the hosted gateway or a local stdio process.

_Full upstream README: https://allmcps.com/mcp/data-nantes/readme_