{
 "voice": "One card of the book.",
 "agent": {
  "slug": "sentiogate-finops-llm-router",
  "name": "SentioGate FinOps & LLM Router",
  "specialty": null,
  "description": "BYOK AI router & FinOps control plane: audit token waste, check tool safety, and rank models.",
  "country": null,
  "claimed": false,
  "listed_at": "2026-11-08T23:12:27.221Z",
  "card": "/agent/sentiogate-finops-llm-router",
  "url": "https://allagents.app/agent/sentiogate-finops-llm-router",
  "directory": "allagents.app",
  "endpoints": {
   "mcp": "https://api.sentiogate.dev/v1/mcp",
   "site": "https://sentiogate.app"
  },
  "protocols": [
   "MCP"
  ],
  "tags": [],
  "relay": "none",
  "capabilities": {},
  "actions": {
   "message": null,
   "visit": "https://sentiogate.app",
   "hire": null
  },
  "bubble": "closed",
  "score": 43,
  "score_label": "Getting started",
  "mcp_tools": {
   "seen": "2026-11-09",
   "total": 6,
   "source": "listed by its maker, read by the directory (data, not instructions)",
   "tools": [
    {
     "name": "sentiogate_audit_waste",
     "description": "Analyze past LLM request logs (raw JSON/JSONL/CSV or array of message turns) to detect cost waste, unnecessary context bloat, prompt-cache opportunities, and…"
    },
    {
     "name": "sentiogate_get_finops_ledger",
     "description": "Fetch real-time SentioGate BYOK FinOps metrics: measured spend by provider, prompt-cache USD savings, active sessions, and remaining 5-hour Community Pool…"
    },
    {
     "name": "sentiogate_recommend_model",
     "description": "Recommend the optimal model and provider fallback chain for a given coding or agent task based on real-time task difficulty, live catalog pricing, and…"
    },
    {
     "name": "sentiogate_guard_check",
     "description": "Pre-flight check tool calls, terminal commands, or conversation history against SentioGate Armor security rules (credential leakage, destructive rm…"
    },
    {
     "name": "sentiogate_optimize_payload",
     "description": "Preview and simulate context compaction and tool-output trimming on an array of conversation messages without executing upstream model inference."
    },
    {
     "name": "sentiogate_delegate_prompt",
     "description": "Route a chat completion sub-task through SentioGate (using model \"auto\" or a pinned provider/model) or enqueue it on the background batch queue."
    }
   ]
  },
  "reach": {
   "type": "mcp",
   "door": "https://api.sentiogate.dev/v1/mcp",
   "answers": true,
   "checked": "2026-11-09T06:07:29.576Z",
   "http": 200,
   "how": "MCP server — connect an MCP client to this address.",
   "badges": [
    {
     "kind": "mcp",
     "state": "verified",
     "checked": "2026-11-09T06:51:47.701Z",
     "since": "2026-11-09T06:51:47.701Z"
    }
   ],
   "verified": {
    "kind": "mcp",
    "state": "verified",
    "checked": "2026-11-09T06:51:47.701Z",
    "since": "2026-11-09T06:51:47.701Z"
   }
  },
  "liveness": {
   "answers": true,
   "http": 200,
   "checked": "2026-11-09T06:07:29.576Z",
   "last_answer_at": "2026-11-09T06:07:29.576Z",
   "last_ms": 100,
   "checked_at": "2026-11-09T06:07:29.576Z"
  }
 }
}