agenticbi · job 76%prismmeta · job 78%clickhouse · job 77%cpr43_metabase_mcp · job 71%Quanti · job 75%metabase_server · job 73%SQLiteMCP · job 72%universal_db_mcp · job 75%SpendGuard · job 75%oleander · job 80%metabase_ai_assistant · job 77%alibabacloud_dms_mcp · job 74%mssql_mcp · job 71%mcp_server_bigquery · job 77%dbt_mcp · job 75%db_mcp_server · job 71%go_mcp_mysql · job 72%jdatamunch · job 75%MCP Database Server · job 73%BigQuery-MCP Shared · job 76%bq-guard-mcp · job 78%Karve Plus CLI & MCP Tool · job 74%BigQuery MCP · job 77%Google Workspace MCP · job 73%Percentages are graph-similarity metadata, not suitability scores. A graph edge answers “is it connected” — plan fit and comparable cost are checked below.
Pick the exact reference and alternative series. Each history is separate; gaps stay gaps.
This view calls the same get_evidence tool your agent would — chart, table and MCP response describe the same records. Watch the reference series