`fetch_dataset`

Pack: oecd · Endpoint: https://gateway.pipeworx.io/oecd/mcp

Fetch tidy rows from any OECD dataflow. flow_ref examples: “OECD.SDD.NAD,DSD_NAMAIN1@DF_QNA_EXPENDITURE_GROWTH,1.0”. The key string is a dot-separated dimension filter (e.g., “USA…Q” — leave empty to fetch everything). Use start/end periods like “2020-Q1” or “2020”. Returns labeled rows; OECD enforces a result-size limit and may truncate broad queries — narrow with key dimensions or shorter time ranges.

Parameters

Name	Type	Required	Description
`flow_ref`	string	yes	SDMX dataflow reference
`key`	string	no	Dot-separated dimension key (or empty for all)
`start_period`	string	no	e.g., “2020”, “2020-Q1”, “2020-01”
`end_period`	string	no	Inclusive end period
`limit`	number	no	Cap rows returned (default 5000)

Example call

Arguments

{
  "flow_ref": "OECD.SDD.NAD,DSD_NAMAIN1@DF_QNA_EXPENDITURE_GROWTH,1.0",
  "key": "USA.....Q",
  "start_period": "2020-Q1",
  "end_period": "2023-Q4"
}

curl

curl -X POST https://gateway.pipeworx.io/oecd/mcp \
  -H 'Content-Type: application/json' \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"fetch_dataset","arguments":{"flow_ref":"OECD.SDD.NAD,DSD_NAMAIN1@DF_QNA_EXPENDITURE_GROWTH,1.0","key":"USA.....Q","start_period":"2020-Q1","end_period":"2023-Q4"}}}'

TypeScript (@pipeworx/sdk)

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

const result = await pipeworx.call('fetch_dataset', {
  "flow_ref": "OECD.SDD.NAD,DSD_NAMAIN1@DF_QNA_EXPENDITURE_GROWTH,1.0",
  "key": "USA.....Q",
  "start_period": "2020-Q1",
  "end_period": "2023-Q4"
});

More examples

{
  "flow_ref": "OECD.ELS,DSD_LFS@DF_ALFS_POPULATION,1.0",
  "key": "",
  "start_period": "2022",
  "end_period": "2024"
}

Response shape

Always returns: flow_ref, source_url, columns, truncated, count, rows

Field	Type	Description
`flow_ref`	string	The requested SDMX dataflow reference
`source_url`	string	URL to OECD data explorer for this flow
`columns`	array	CSV column headers
`truncated`	boolean	True if result was limited by row cap
`count`	number	Number of data rows returned
`rows`	array	Data rows with column names as keys

Full JSON Schema

{
  "type": "object",
  "properties": {
    "flow_ref": {
      "type": "string",
      "description": "The requested SDMX dataflow reference"
    },
    "source_url": {
      "type": "string",
      "description": "URL to OECD data explorer for this flow"
    },
    "columns": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "CSV column headers"
    },
    "truncated": {
      "type": "boolean",
      "description": "True if result was limited by row cap"
    },
    "count": {
      "type": "number",
      "description": "Number of data rows returned"
    },
    "rows": {
      "type": "array",
      "items": {
        "type": "object",
        "additionalProperties": {
          "type": "string"
        }
      },
      "description": "Data rows with column names as keys"
    }
  },
  "required": [
    "flow_ref",
    "source_url",
    "columns",
    "truncated",
    "count",
    "rows"
  ]
}

Connect

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

{
  "mcpServers": {
    "oecd": {
      "url": "https://gateway.pipeworx.io/oecd/mcp"
    }
  }
}

See Getting Started for client-specific install steps.

fetch_dataset