Context Intelligence

list_ci_findings

List Context Intelligence findings — issues Marcora's automated scans detected in your reference library (stale content, contradictions, outdated web sources, gaps). Newest-first; filter by status, severity, or scan type.

Input Schema

{
  "type": "object",
  "properties": {
    "page": {
      "type": "integer",
      "description": "Page number (default 1)."
    },
    "status": {
      "type": "string",
      "description": "Filter by finding status: pending (actionable queue) | acknowledged | dismissed | resolved. Omit for all."
    },
    "per_page": {
      "type": "integer",
      "description": "Items per page (default 20, max 100)."
    },
    "severity": {
      "type": "string",
      "description": "Filter by severity as recorded by the scan (e.g. high, medium, low). Omit for all."
    },
    "process_type": {
      "type": "string",
      "description": "Filter by originating scan: health_audit (library-wide sweep) | web_freshness (tracked webpage changes). Omit for all."
    }
  }
}

Output Schema

{
  "type": "object",
  "properties": {
    "items": {
      "type": "array",
      "description": "Finding objects: id (UUID), summary, recommendation, severity, status, process_type, finding_type, suggested_fix, context_item_ids, created_at, resolved_at, resolved_by."
    },
    "curPage": {
      "type": "integer"
    },
    "nextPage": {
      "type": [
        "integer",
        "null"
      ]
    },
    "prevPage": {
      "type": [
        "integer",
        "null"
      ]
    },
    "itemsTotal": {
      "type": "integer"
    }
  }
}

Instructions

List Context Intelligence findings for your team — issues Marcora's automated scans detected in your reference/context library (stale content, contradictions, outdated web sources, classification gaps).

Use this when the user asks about their context health, what Context Intelligence found, open findings, or what needs attention in their reference library. It's also the right first call before updating any finding's status (to get the finding's UUID).

Findings are returned newest-first. Each has a status lifecycle: pending (new, needs review) → acknowledged / dismissed / resolved.

Filters (all optional):

status — pending (the actionable queue) | acknowledged | dismissed | resolved.
severity — as recorded by the scan (e.g. high, medium, low).
process_type — which scan produced it: health_audit (library-wide sweep) | web_freshness (tracked webpage changes).
page / per_page — pagination. Default per_page=20, max 100.

Example prompts:

“What did Context Intelligence find in our reference library?”
“Show me the open (pending) context findings.”
“Any high-severity issues from the last health audit?”