{
"event": "PreToolUse",
"tool_name": "mcp__mcp-db__db_select",
"tool_input": {
"query": "SELECT \n pc.id, pc.name,\n COUNT(ps.id) as step_count,\n GROUP_CONCAT(ps.step_type ORDER BY ps.sort_order SEPARATOR ', ') as steps\nFROM pipeline_configs pc\nLEFT JOIN pipeline_steps ps ON pc.id = ps.pipeline_id\nGROUP BY pc.id",
"database": "ki_content"
}
}
{
"tool_response": [
{
"type": "text",
"text": "{\n \"status\": \"success\",\n \"data\": [\n {\n \"id\": 1,\n \"name\": \"Standard\",\n \"step_count\": 5,\n \"steps\": \"detect, extract, chunk, embed, analyze\"\n },\n {\n \"id\": 2,\n \"name\": \"Schulungsunterlagen\",\n \"step_count\": 20,\n \"steps\": \"detect, validate, page_split, vision_analyze, extract, structure, segment, chunk, metadata_store, embed, collection_setup, vector_store, index_optimize, knowledge_page, knowledge_section, knowledge_document, knowledge_validate, summarize, question_generate, finalize\"\n },\n {\n \"id\": 3,\n \"name\": \"Vollständiger RAG-Prozess\",\n \"step_count\": 25,\n \"steps\": \"detect, validate, extract, page_split, vision_analyze, structure, segment, chunk, metadata_store, embed, collection_setup, vector_store, index_optimize, entity_extract, relation_extract, semantic_analyze, knowledge_page, knowledge_section, knowledge_document, knowledge_validate, taxonomy_build, analyze, summarize, question_generate, finalize\"\n }\n ],\n \"row_count\": 3,\n \"error\": null,\n \"execution_ms\": 0\n}"
}
]
}