Demo workspaceSample data for Kestrel Pay, a fictional bank. Nothing here is a live customer feed.
Exit demoStart your workspace

Signal workspace

API and MCP

Cases, evidence, and surface health are readable from your own systems. The schema below is the one this workspace returns.

GET /api/v1/cases/kp-4821

200
{
  "id": "KP-4821",
  "threatType": "impersonation-account",
  "severityScore": 94,
  "relevanceScore": 0.98,
  "status": "escalated",
  "surface": "tiktok",
  "canonicalUrl": "https://www.tiktok.com/@kestrelpay.rewards/video/7481102934",
  "classifierReason": "Profile reproduces the official avatar and bio, claims to act for th...",
  "harmSignals": ["credential-request","money-solicitation","official-insignia","high-reach"],
  "classifierVersion": "sentinel-threat-v1",
  "evidence": [
    { "kind": "screenshot", "payloadHash": "sha256:41b98070...f48a21" }
  ]
}

MCP connection

Search cases, inspect a classification, and read surface health from any MCP client.

{
  "mcpServers": {
    "sentinely": {
      "command": "npx",
      "args": ["-y", "@sentinely/mcp"],
      "env": { "SENTINELY_API_KEY": "sk_live_..." }
    }
  }
}

Scopes

Keys are read-only by default. Escalation and status transitions stay in the workspace, where the role model applies.

cases:read

Case records, classifications, and status

evidence:read

Capture metadata and payload digests

health:read

Per-surface collection state and freshness