`query`

Pack: data-sncf · Endpoint: https://gateway.pipeworx.io/data-sncf/mcp

Query records from a SNCF Open Data dataset with ODSQL. Filter (where), aggregate (group_by/select), sort (order_by), paginate (limit/offset).

Parameters

Name	Type	Required	Description
`dataset_id`	string	yes	Dataset id from search_datasets.
`query`	string	no	Free-text keyword across all fields (optional).
`where`	string	no	ODSQL filter, e.g. `year >= 2020 AND city = "Paris"` (overrides query).
`select`	string	no	ODSQL select/aggregation, e.g. `count(*) as n, sum(amount)`.
`group_by`	string	no	ODSQL group_by field(s).
`order_by`	string	no	Sort, e.g. `date desc`.
`limit`	number	no	Max records (1-100, default 20).
`offset`	number	no	Pagination offset (default 0).

Example call

Arguments

{
  "dataset_id": "sncf-open-data-train-schedules",
  "where": "year >= 2020",
  "limit": 50
}

curl

curl -X POST https://gateway.pipeworx.io/data-sncf/mcp \
  -H 'Content-Type: application/json' \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"query","arguments":{"dataset_id":"sncf-open-data-train-schedules","where":"year >= 2020","limit":50}}}'

TypeScript (@pipeworx/sdk)

import { Pipeworx } from '@pipeworx/sdk';
const pipeworx = new Pipeworx();

const result = await pipeworx.call('query', {
  "dataset_id": "sncf-open-data-train-schedules",
  "where": "year >= 2020",
  "limit": 50
});

More examples

{
  "dataset_id": "sncf-open-data-punctuality",
  "select": "count(*) as total, avg(delay_minutes) as avg_delay",
  "group_by": "station",
  "order_by": "avg_delay desc"
}

Connect

Add this to your MCP client config, or use one-click install buttons:

{
  "mcpServers": {
    "data-sncf": {
      "url": "https://gateway.pipeworx.io/data-sncf/mcp"
    }
  }
}

See Getting Started for client-specific install steps.

query