mcp-server

Search the company's connected knowledge across every source — Drive, SharePoint, Confluence, Slack, Notion — with cited synthesized answers, lifecycle awareness, and refusal-on-weak-context. Returns a written answer with [n] citations plus the ranked source chunks. Modes: `fast` (1,500 kT — retrieval-only, no synthesis), `standard` (12,500 kT — default; synthesized answer over the top retrieval set), `deep` (25,000 kT — wider retrieval + premium synthesis for complex questions). Pick the cheapest tier that answers the question. Responses are capped at 25,000 output tokens per Claude Connectors policy; if truncated, structured metadata carries `truncated: true` and `query_id` so the agent can call `get_source_detail` for full provenance.

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "description": "Natural-language query (1–2000 characters). Be specific — results are ranked by authority + relevance, not keyword overlap."
    },
    "mode": {
      "type": "string",
      "description": "fast | standard | deep. Defaults to `standard`. `fast` returns chunks only (no synthesized answer); `standard` and `deep` return a synthesized answer with [n] citations + the source chunks.",
      "enum": [
        "fast",
        "standard",
        "deep"
      ]
    },
    "max_sources": {
      "type": "number",
      "description": "Number of source chunks to return (1–20, default 5). The 25K token cap may force fewer results regardless of this value.",
      "minimum": 1,
      "maximum": 20
    },
    "domain": {
      "type": "string",
      "description": "Optional taxonomy domain filter (e.g. 'engineering.platform'). Use `list_domains` to discover valid values for the tenant."
    }
  },
  "required": [
    "query"
  ]
}

List the taxonomy domains the company has indexed — with document counts, expert counts, and coverage levels — so an agent can decide whether to query before spending a Knowledge Token. Returns one row per domain with the canonical `taxonomy_domain` slug, document/chunk counts, expert count, coverage level (expert | partial | none), the single_expert risk flag, and the top contributor by authority. Use the slug as the `domain` filter on a follow-up `query_knowledge` call. Zero Knowledge Tokens consumed.

{
  "type": "object",
  "properties": {
    "coverage_filter": {
      "type": "string",
      "description": "Optional comma-separated subset of expert,partial,none. Default: all three. Unknown tokens 400."
    }
  },
  "required": []
}

Return per-chunk source provenance for a previous query — document path, lifecycle state, embedding timestamp, contributor, last-updated — useful for verifying a citation or surfacing trust signals to a downstream system. Pass a `query_id` returned by an earlier `query_knowledge` call. Returns 404 if the query_id is unknown OR belongs to a different tenant (indistinguishable to prevent info-leak). Zero Knowledge Tokens consumed.

{
  "type": "object",
  "properties": {
    "query_id": {
      "type": "string",
      "description": "UUID returned in the structured-metadata block of a prior `query_knowledge` response. Tenant-scoped — cross-tenant 404."
    }
  },
  "required": [
    "query_id"
  ]
}