get_oracle_findings

ai.athenahq/mcp · Verify this server

When grounding is present, use its complete team-confirmed statement and all supporting facts as joint evidence; the legacy fact ID/text are only a compatibility anchor. List Oracle accuracy findings for a website: places where an AI response contradicted a verified brand fact (type 'inaccuracy' or 'kb_issue', with quote, claim, and reason) or where two knowledge-base facts conflict ('kb_duplicate' / 'kb_contradiction', pairing fact_text with related_fact_text). Findings from every status are included by default (pending, acknowledged, ignored, ...), each row carrying its status — pass the status filter for pending items only. Filters (run_id, fact_id, lineage_id, response_id, prompt_id, source_url, type, kind, severity, status) AND-compose; source_url matches evidence URLs exactly after normalization (protocol and trailing slash ignored). 'total' is the pre-limit count. 'latest_run' is the newest scan of any kind and is null only when the website has never been scanned, so latest_run plus empty findings means it scanned clean, while latest_run null means never scanned, not clean. Archived findings from before the current scanner ARE included: their run carries 'is_imported': true and keeps its original started_at, so an import can be the newest run — say the history is archived rather than calling it a current scan. 'has_imported_history' is true when any such archived run exists, and every finding row carries 'run_is_imported' so archival and current rows stay distinguishable in one list. Returns status 'no_access' if the brand does not have Oracle v2; that response carries the status alone, with no counts or findings.