Documentation menu
Reference / v0.1

MCP tool reference

Six tools, all bounded by the calling customer key and its scopes.

Reviewed September 16, 2026 · Current implementation

Available tools

ToolArgumentsScope
recursift_fleet_overview{}agents:read
recursift_list_agentscursor?, limit?agents:read
recursift_ask_agentagent_id, questionquery:write
recursift_ask_fleetagent_ids, question, timeout_seconds?query:write
recursift_get_queryquery_idquery:read
recursift_search_findingssearch?, cursor?, limit?query:read

Discovery and presence

Fleet overview reports presence counts for the first 100 accessible endpoints, plus next_cursor. It is not a complete fleet census when another page exists. Use list_agents pagination to enumerate further endpoints. Tool discovery currently lists all six tools; invocation still enforces scopes.

Asynchronous questions

ask_agent and ask_fleet return a job receipt immediately. ask_fleet requires 1–100 explicit endpoint IDs and accepts a 5–120 second timeout. get_query accepts the receipt’s id as query_id; it returns current findings, counts and unanswered IDs. Questions are at most 500 characters.

Fleet request arguments
{
  "agent_ids": [
    "ENDPOINT_A",
    "ENDPOINT_B"
  ],
  "question": "What operating system are you running?",
  "timeout_seconds": 120
}

Stored finding search

search_findings searches materialized API answer summaries by substring. It does not collect new endpoint evidence or run local vector retrieval. It returns findings, next_cursor and a coverage explanation. No result is not evidence of absence.

Continue readingIntegration examples