# Data Rennes [Health: Active]

**Category:** 📊 Data Platforms  
**Repository:** https://github.com/pipeworx-io/mcp-data-rennes  
**GitHub Stars:** 0  
**npm Downloads (last month):** 443  
**Views:** 2  
**Installs:** 0  
**Upvotes:** 0  
**Directory Page:** https://allmcps.com/mcp/data-rennes

## Description
Rennes Métropole Open Data (data.rennesmetropole.fr) — OpenDataSoft MCP.

## Tools
Capabilities this server exposes over MCP:

- **search_datasets** — Search Rennes 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 Rennes Métropole Open Data dataset (fields/schema, themes, record count) — call before query to learn the column names.
- **query** — Query records from a Rennes 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-rennes": {
    "command": "npx",
    "args": ["-y","@pipeworx/mcp-data-rennes"]
  }
}
```

## Documentation

## What Data Rennes does

Data Rennes exposes Rennes Métropole Open Data through three focused MCP tools. It helps an agent locate relevant datasets, understand their available fields, and retrieve or summarize records. The connected catalog covers subjects such as mobility, urban services, environment, and geography.

The integration is unofficial and independent of the upstream data provider. It uses the Rennes Métropole Open Data service at data.rennesmetropole.fr as its source.

## How it works

The recommended workflow is to search first, inspect the selected dataset, then query it. `search_datasets` returns dataset identifiers along with titles, themes, and record counts. Pass a returned identifier to `dataset_info` to see the dataset schema and learn the exact column names before writing a query.

`query` accepts ODSQL options for record filtering, grouping and selection, ordering, and pagination. This supports both row-level retrieval and basic aggregations. The gateway also offers `ask_pipeworx`, which can accept a plain-language question and select and populate an appropriate tool across the Pipeworx catalog.

## Setup and configuration

A hosted streamable HTTP endpoint is available at:

```text
https://gateway.pipeworx.io/data-rennes/mcp
```

For example, an MCP client configuration can point the `data-rennes` entry at that URL:

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

The hosted endpoint can also expose shared Pipeworx meta-tools in addition to the three Data Rennes tools. A full gateway connection is available at `https://gateway.pipeworx.io/mcp`; both endpoints use the same gateway and source catalog, while their directly listed pack tools differ.

For a local installation, run the npm package with `npx`:

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

The local process communicates over stdin and stdout and exposes only the Data Rennes pack tools. The hosted route does not require an account for initial calls. The tools can also be called over HTTP through the gateway's `/v1/tools/` endpoints.

## Tools and capabilities

- `search_datasets`: Find Rennes Métropole datasets by keyword and return identifiers, names, themes, and record totals.
- `dataset_info`: Retrieve metadata, including fields, schema details, themes, and record count, for one dataset.
- `query`: Read dataset records using ODSQL, including `where` filters, `group_by` and `select` operations, `order_by` sorting, and `limit`/`offset` pagination.
- `ask_pipeworx`: On gateway connections, submit a natural-language request for routing across the broader Pipeworx catalog.

## Limitations and notes

The gateway pack endpoint lists shared Pipeworx meta-tools alongside the Data Rennes tools, so its tool list can be substantially larger than the three pack-specific operations. The local stdio mode avoids those gateway-wide tools and provides only the pack's own operations.

Dataset field names should be obtained with `dataset_info` before composing ODSQL queries. Results and available records depend on the Rennes Métropole Open Data catalog. Data Rennes is an unofficial integration and is not presented as an upstream Rennes Métropole product.

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