query_dataset

Active

declared in 0.1.0

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 schema

{
  "type": "object",
  "required": [
    "matrix",
    "filters"
  ],
  "properties": {
    "matrix": {
      "type": "string",
      "description": "Matrix code, e.g. \"CPM01\"."
    },
    "filters": {
      "type": "object",
      "description": "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\")."
    }
  }
}

What this tool wraps· 0 endpoints

min confidence0.70 0.50

No endpoints wrapped at confidence ≥ 0.70.

Parent server

Cso Ie

https://github.com/pipeworx-io/mcp-cso-ie

1/7 registries

View full server →