run_query
Execute SQL queries on CSV or Parquet sources using DuckDB syntax via the Zaturn MCP server, returning results as a dataframe for analysis and visualization.
Instructions
Run query against specified source For both csv and parquet sources, use DuckDB SQL syntax Use 'CSV' as the table name for csv sources. Use 'PARQUET' as the table name for parquet sources.
This will return a dataframe with the results.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | SQL query to run on the data source | |
| source_id | Yes | The data source to run the query on |
Input Schema (JSON Schema)
{
"properties": {
"query": {
"description": "SQL query to run on the data source",
"title": "Query",
"type": "string"
},
"source_id": {
"description": "The data source to run the query on",
"title": "Source Id",
"type": "string"
}
},
"required": [
"source_id",
"query"
],
"type": "object"
}