query_metrics

ai.athenahq/mcp · Verify this server

Query aggregated metrics for brand performance, competitors, sources, citations, and response trends. Use query_rows for individual records. Mentions: from "response_mentions". Citations: from "citations". On either, where { is_website: true } selects the brand; { is_competitor: true } selects competitors; { entity_id: { eq: "<uuid>" } } selects one entity. Filter/group models by model_category (display names like "ChatGPT", "Claude"), never "model". Dimensions vary by cube; source_mentions has no prompt/model dimensions. Measures: count, count_distinct, avg, sum, min, max; per-measure where enables conditional aggregation. Use compare for two date ranges. When grouping by IDs, use alsoSelect for names: entity_id/entity_name, prompt_id/prompt_text, prompt_topic_id/topic_name (prompts uses topic_id). Cited pages mentioning competitors but not the brand: from "sources", where { source_mentions_entity: { hasSome: [competitorIds], hasNone: [brandId] } }. Also works on "source_mentions". Checks all stored page mentions per URL/website. Date/model on sources scope AI responses; extracted page content may be older than the live page. Content-hub attribution: on "sources", where { is_attributed_content: true }; by: ["content_id"], alsoSelect: ["content_title"]. Add content_type to by for type, or group by content_type alone. Read articles from "contents" via query_rows. Schedule: select one "default" or custom/archived UUID from the catalog, or an array of them to combine schedules. Omit for caller default (current page in Ask Athena); explicit schedule overrides it. Top-level prompt_schedule_kind/id equality filters remain supported but must not conflict with schedule. Historical provenance is independent of current prompt membership; website-level cubes are unaffected.