query_log_file
Runs high-speed SQL queries against log files in JSONL, CSV, or Parquet format to extract insights and troubleshoot issues directly from local data without manual parsing.
Instructions
Executes high-speed DuckDB SQL queries directly against log files (JSONL, CSV, Parquet).
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"file_path": "<file_path>",
"sql_query": "<sql_query>"
},
"name": "query_log_file"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| max_rows | No | Hard cap on return records to prevent LLM context bloat (default: 100). | |
| file_path | Yes | Host file path to target log file. | |
| sql_query | Yes | DuckDB SQL statement. Example: "SELECT level, count(*) FROM read_json_auto('app.json') GROUP BY level" |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |