oecd_query
Pack: oecd · Connect: https://pipeworx.io/mcp (see Connect below for a single-pack URL)
No MCP client? Call it directly: GET https://gateway.pipeworx.io/v1/tools/oecd_query for the schema, then POST the same URL with its arguments for the data.
Fetch OECD observations by NAMED dimensions instead of a positional key. filters maps dimension id to a code or a name (or an array): {REF_AREA:“Korea”, SECTOR:“S13”, STANDARD_REVENUE:“T_1100”, UNIT_MEASURE:“PT_B1GQ”, FREQ:“A”}. Unmentioned dimensions are wildcards. Names resolve against the flow’s own code list; an unknown dimension, an unmatched or ambiguous value is refused with the valid dimensions and candidates, nothing is queried. Copy these flow_refs exactly. Tax revenue (tax as % of GDP) flow_ref “OECD.CTP.TPS,DSD_REV_COMP_OECD@DF_RSOECD,2.0”: dims REF_AREA, MEASURE (TAX_REV), SECTOR (S13), STANDARD_REVENUE (T_1100 personal income tax), CTRY_SPECIFIC_REVENUE, UNIT_MEASURE (PT_B1GQ = % of GDP), FREQ. Quarterly sector accounts “OECD.SDD.NAD,DSD_NASEC1@DF_QSA,1.1”: dims FREQ, ADJUSTMENT, REF_AREA, SECTOR (S11 non-financial corporations), COUNTERPART_SECTOR, ACCOUNTING_ENTRY, TRANSACTION (B9 net lending/borrowing), INSTR_ASSET, UNIT_MEASURE. Merchandise trade (goods imports/exports, G20/OECD/World aggregates) “OECD.SDD.TPS,DSD_IMTS@DF_IMTS,1.0”: dims REF_AREA (G20), COUNTERPART_AREA (W), TRADE_FLOW (M imports, X exports), FREQ (Q), UNIT_MEASURE (USD_EXC). Services trade incl. G20 aggregate “OECD.SDD.TPS,DSD_BOP@DF_BOP,1.1”: dims REF_AREA (G20), MEASURE (S services), ACCOUNTING_ENTRY (C exports, D imports), FREQ, UNIT_MEASURE (USD_EXC). A wrong agency/version of a known flow id is corrected and reported as flow_ref_resolved; obvious dimension-name aliases (COUNTRY, FLOW, ENTRY) are mapped and reported. start_period like “2007”, “2021-Q2”.
Parameters
| Name | Type | Required | Description |
|---|---|---|---|
flow_ref | string | yes | SDMX dataflow reference, e.g. “OECD.CTP.TPS,DSD_REV_COMP_OECD@DF_RSOECD,2.0” |
filters | object | yes | Dimension id -> code, name, or array of either, e.g. {“REF_AREA”:“KOR”,“UNIT_MEASURE”:“PT_B1GQ”} |
start_period | string | no | e.g. “2007”, “2021-Q2”, “2020-01” |
end_period | string | no | Inclusive end period |
limit | number | no | Cap rows returned (default 200) |
Example call
Arguments
{
"flow_ref": "OECD.CTP.TPS,DSD_REV_COMP_OECD@DF_RSOECD,2.0",
"filters": {
"REF_AREA": "South Korea",
"MEASURE": "TAX_REV",
"SECTOR": "S13",
"STANDARD_REVENUE": "T_1100",
"UNIT_MEASURE": "PT_B1GQ",
"FREQ": "A"
},
"start_period": "2007",
"end_period": "2007"
}
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":"oecd_query","arguments":{"flow_ref":"OECD.CTP.TPS,DSD_REV_COMP_OECD@DF_RSOECD,2.0","filters":{"REF_AREA":"South Korea","MEASURE":"TAX_REV","SECTOR":"S13","STANDARD_REVENUE":"T_1100","UNIT_MEASURE":"PT_B1GQ","FREQ":"A"},"start_period":"2007","end_period":"2007"}}}'
TypeScript (@pipeworx/sdk)
import { Pipeworx } from '@pipeworx/sdk';
const pipeworx = new Pipeworx();
const result = await pipeworx.call('oecd_query', {
"flow_ref": "OECD.CTP.TPS,DSD_REV_COMP_OECD@DF_RSOECD,2.0",
"filters": {
"REF_AREA": "South Korea",
"MEASURE": "TAX_REV",
"SECTOR": "S13",
"STANDARD_REVENUE": "T_1100",
"UNIT_MEASURE": "PT_B1GQ",
"FREQ": "A"
},
"start_period": "2007",
"end_period": "2007"
});
More examples
{
"flow_ref": "OECD.SDD.TPS,DSD_IMTS@DF_IMTS,1.0",
"filters": {
"REF_AREA": "G20",
"COUNTERPART_AREA": "World",
"TRADE_FLOW": "Imports",
"FREQ": "Quarterly",
"UNIT_MEASURE": "USD_EXC",
"ADJUSTMENT": "N"
},
"start_period": "2021-Q2",
"end_period": "2021-Q2"
}
Response shape
| Field | Type | Description |
|---|---|---|
flow_ref | string | |
key_used | string | |
resolved_filters | object | |
columns | array | |
count | number | |
truncated | boolean | |
rows | array | |
source_url | string | |
error | string | |
message | string | |
dimensions | array | |
problems | array | |
empty_reason | string | |
note | string |
Full JSON Schema
{
"type": "object",
"additionalProperties": true,
"properties": {
"flow_ref": {
"type": "string"
},
"key_used": {
"type": "string"
},
"resolved_filters": {
"type": "object",
"additionalProperties": true
},
"columns": {
"type": "array",
"items": {
"type": "string"
}
},
"count": {
"type": "number"
},
"truncated": {
"type": "boolean"
},
"rows": {
"type": "array",
"items": {
"type": "object",
"additionalProperties": true
}
},
"source_url": {
"type": "string"
},
"error": {
"type": "string"
},
"message": {
"type": "string"
},
"dimensions": {
"type": "array",
"items": {
"type": "object",
"additionalProperties": true
}
},
"problems": {
"type": "array",
"items": {
"type": "object",
"additionalProperties": true
}
},
"empty_reason": {
"type": "string"
},
"note": {
"type": "string"
}
}
}
Connect
Add this to your MCP client config — every tool in the catalog, including this one — or use one-click install buttons:
{
"mcpServers": {
"pipeworx": {
"url": "https://pipeworx.io/mcp"
}
}
}
Connect to just the oecd pack
{
"mcpServers": {
"oecd": {
"url": "https://gateway.pipeworx.io/oecd/mcp"
}
}
}
See Getting Started for client-specific install steps.