Data Rennes logo

Data Rennes

Query Rennes Métropole Open Data datasets through MCP tools for discovery, metadata, filtering, aggregation, sorting, and pagination.

Install Data Rennes

Pick your client, then add it in one click or paste the config.

STDIONode.js
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "data-rennes": {
      "command": "npx",
      "args": [
        "-y",
        "@pipeworx/mcp-data-rennes"
      ]
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

Automated check passed— started and listed 3 tools correctly (7d ago).

Overview

The Data Rennes MCP server connects AI clients to Rennes Métropole Open Data at data.rennesmetropole.fr through the OpenDataSoft API. It supports dataset discovery, schema inspection, and ODSQL record queries with filtering, aggregation, sorting, and pagination. Use it when an agent needs current Rennes-area data about mobility, urban services, environment, or geography. It is available as a hosted MCP endpoint or a local stdio package.

Use cases

  • Find datasets about Rennes mobility services
  • Inspect fields before writing an ODSQL query
  • Filter and paginate municipal open-data records
  • Aggregate environmental or geographic records
  • Connect an MCP client to Rennes Métropole data

Key features

  • Dataset search by keyword
  • Dataset schema and metadata inspection
  • ODSQL record queries
  • Filtering, aggregation, and field selection
  • Sorting and pagination
  • Hosted HTTP and local stdio modes

Tools3

What Data Rennes lets your agent do. Expand a tool for its parameters.

Verified live~417 tokens of context

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked 3d ago

Recent health check succeeded.

7/7 checks healthy over the last 46d

What it can do

From the 3 tools this server returned when we ran it.

Read-only tools · 3
Network at startup3 connections
Files written at startupNone
Install scriptsNone
npm provenanceSigned build
Package age112 days
Maintainers1

Observed 2026-10-17 in an isolated sandbox. A description of reach, not a security audit.

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 15d ago via OSV.dev · @pipeworx/mcp-data-rennes (npm)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

npm downloads443Package downloads in the last 30 days.
Last commit28d agoMost recent push to the default branch.
Availability100%Our rolling endpoint + install checks that succeeded.
Install checkPassedOur sandbox started it and listed its tools.
Tools exposed3Callable tools this server registers over MCP.
Directory activity2 viewsConfig copies, upvotes, and views on AllMCPs.

How Data Rennes works

What the Data Rennes MCP server does

The Data Rennes MCP server gives an MCP-compatible agent access to Rennes Métropole’s public datasets on data.rennesmetropole.fr. Its main workflow is discovery first, inspection second, and querying third. An agent can search for relevant datasets, examine a selected dataset’s fields and metadata, then request records using the available column names.

The service is suited to questions involving local mobility, urban services, environmental information, and geographic data. Search results include dataset identifiers, titles, themes, and record counts, which helps an agent choose a dataset before attempting a query.

How it works

The hosted endpoint is provided through the Pipeworx gateway at https://gateway.pipeworx.io/data-rennes/mcp. A client connects over MCP and can call the pack’s three documented tools: search_datasets, dataset_info, and query.

The recommended sequence is to call search_datasets with a keyword, pass a returned identifier to dataset_info, and use the schema from that response to construct a query call. Queries use ODSQL and can filter records with where, aggregate or select fields with group_by and select, order results with order_by, and paginate through results with limit and offset.

The gateway endpoint also exposes shared Pipeworx meta-tools in addition to the pack-specific tools. These include routing and discovery functions such as ask_pipeworx, discover_tools, and search_within. The local package exposes only the Data Rennes tools and does not add those gateway tools.

Setup and configuration

For a hosted connection, add the following MCP server URL to a compatible client:

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

The Data Rennes MCP server can also run locally over stdio with the published npm package:

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

Run npx -y @pipeworx/mcp-data-rennes directly to verify that the local process starts. The standalone mode does not require a Pipeworx account or a gateway round trip. No account is needed for the first gateway calls.

Tools and capabilities

  • search_datasets: Find Rennes Métropole datasets by keyword and return identifiers, titles, themes, and record counts.
  • dataset_info: Inspect a dataset’s fields, schema, themes, and record count.
  • query: Retrieve or summarize records with ODSQL filters, grouping, field selection, ordering, limits, and offsets.

Limitations and notes

The hosted pack endpoint lists shared Pipeworx tools alongside its three documented tools, so its tool list is larger than the local package’s list. Its initialize response provides the authoritative scope for a particular connection. The local stdio mode is limited to this pack’s tools and does not provide ask_pipeworx routing.

Queries depend on the dataset’s actual schema. Call dataset_info before query when the required column names are unknown. The available content is limited to datasets published by Rennes Métropole Open Data and the query features supported by the OpenDataSoft interface.

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Data Rennes

Data Rennes is an MCP server that connects AI clients to Rennes Métropole Open Data at data.rennesmetropole.fr. Its main tools search datasets, inspect dataset metadata and schemas, and query records with ODSQL filters, aggregation, sorting, field selection, and pagination for local public-data research.

Install it locally by configuring an MCP client to run `npx -y @pipeworx/mcp-data-rennes`. The package communicates over stdin and stdout and does not require a Pipeworx account. You can instead configure the hosted MCP URL at `https://gateway.pipeworx.io/data-rennes/mcp`.

Yes, Data Rennes works with Cursor through the hosted MCP endpoint. Add `https://gateway.pipeworx.io/data-rennes/mcp` as an MCP server in the client configuration, or use the local stdio package with the documented `npx` command.

First call `search_datasets` to find a dataset, then call `dataset_info` to learn its fields and schema, and finally use `query` with ODSQL. The query tool supports `where`, `group_by`, `select`, `order_by`, `limit`, and `offset`.

Related MCP servers

Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewData Rennes AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/data-rennes?style=directory)](https://allmcps.com/mcp/data-rennes)
HTML Embed
<a href="https://allmcps.com/mcp/data-rennes"><img src="https://allmcps.com/api/badge/data-rennes?style=directory" alt="Data Rennes on AllMCPs" /></a>