`query_dataset`

Pack: cso-ie · Endpoint: https://gateway.pipeworx.io/cso-ie/mcp

Read a FILTERED slice of a CSO table via JSON-RPC. Pass a map of dimension code -> array of category index values to keep (get the dimension codes and category index values from dataset_metadata). Returns JSON-stat 2.0 covering only the selected cells — far smaller than get_dataset.

Parameters

Name	Type	Required	Description
`matrix`	string	yes	Matrix code, e.g. “CPM01”.
`filters`	object	yes	Map of dimension code to an array of category index values to keep, e.g. {“STATISTIC”:[“CPM01C08”],“TLIST(M1)”:[“202512”]}. Dimensions you omit are returned in full. Time dimensions like TLIST(M1) use YYYYMM index values (e.g. “202512”).

Example call

Arguments

{
  "matrix": "CPM01",
  "filters": {
    "STATISTIC": [
      "CPM01C08"
    ],
    "TLIST(M1)": [
      "202512"
    ]
  }
}

curl

curl -X POST https://gateway.pipeworx.io/cso-ie/mcp \
  -H 'Content-Type: application/json' \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"query_dataset","arguments":{"matrix":"CPM01","filters":{"STATISTIC":["CPM01C08"],"TLIST(M1)":["202512"]}}}}'

TypeScript (@pipeworx/sdk)

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

const result = await pipeworx.call('query_dataset', {
  "matrix": "CPM01",
  "filters": {
    "STATISTIC": [
      "CPM01C08"
    ],
    "TLIST(M1)": [
      "202512"
    ]
  }
});

More examples

{
  "matrix": "QLF18",
  "filters": {
    "TLIST(A1)": [
      "2023"
    ]
  }
}

Connect

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

{
  "mcpServers": {
    "cso-ie": {
      "url": "https://gateway.pipeworx.io/cso-ie/mcp"
    }
  }
}

See Getting Started for client-specific install steps.

query_dataset