Heartbeat — dead-man switch for cron jobs & AI agents

Dead-man switch monitors for cron & AI agents with dependency-cascade alerts. No account needed.

Sollte ich dies verwenden

Qualität und Sicherheit

A
Qualität der Beschreibung
100%
Vollständigkeit des Schemas
92%
Qualität der Benennung
96%
Risiko der Vergiftung
60%
Übereinstimmung der Berechtigungen
100%
Einhaltung des Protokolls
100%

Befunde (3)

  • HIGHTool poisoning patterns detected
  • MEDIUMTool description contains URL to non-standard domainin ping_heartbeat
  • MEDIUMTool description contains URL to non-standard domainin record_failure

Basierend auf einer automatisierten Analyse der Tool-Definitionen und der Einhaltung des Protokolls.

Kontextkosten

~911Tokens (Tool-Definitionen)
~1.3 KBTypische Antwortgröße
Mittlere Auswirkung auf die Aufmerksamkeit (0.71% von 128k Kontext)

Dies ist die ungefähre Anzahl der Tokens, die jedes Mal verbraucht werden, wenn die Tools des Servers in den Kontext eines Modells geladen werden. Höhere Werte verringern die Aufmerksamkeit, die für andere Aufgaben verfügbar ist.

Installieren

Installation mit einem Klick

Fügen Sie dies Ihrer Datei `claude_desktop_config.json` hinzu:

{
  "mcpServers": {
    "golemreach-heartbeat": {
      "url": "https://golemreach.com/heartbeat/mcp"
    }
  }
}

Remote-Endpunkte

https://golemreach.com/heartbeat/mcpstreamable-http

Was es kann

Tool-Inventar

Tools (5)

🟢 Nur lesen🟡 Schreiben🔴 Löschen⚪ Unbekannt
🟡create_heartbeat(name, period_s, grace_s, kind, target_url, ...)

Arm a new dead-man switch monitor. Returns the key plus a ping_url your job must hit after every run. No account needed. Names are globally unique on this instance and each name gets a PUBLIC status page; the secret key is the only credential — keep it.

Eingabe-Schema

{
  "type": "object",
  "properties": {
    "name": {
      "type": "string",
      "description": "unique name, 1-40 chars [A-Za-z0-9_.-]"
    },
    "period_s": {
      "type": "integer",
      "description": "expected seconds between pings (60-86400)",
      "default": 300
    },
    "grace_s": {
      "type": "integer",
      "description": "extra seconds of slack before DOWN (0-86400)",
      "default": 300
    },
    "kind": {
      "type": "string",
      "enum": [
        "push",
        "pull",
        "selfcheck"
      ],
      "description": "push = you ping us; pull = we probe target_url every min(period_s,60)s; selfcheck = your box runs our egress-trust probe script and POSTs verdict reports to the ping URL",
      "default": "push"
    },
    "target_url": {
      "type": "string",
      "description": "public http(s) URL to probe (pull only)"
    },
    "webhook_url": {
      "type": "string",
      "description": "public http(s) URL that receives UP/DOWN alerts (optional)"
    },
    "depends_on": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "parent monitor names and/or gate:<gate-name> entries (max 5). When a parent is DOWN or a gate parent is HALT this monitor becomes DEGRADED-BY-UPSTREAM: notified once, own silence paging suppressed until the parent recovers."
    },
    "pass_key": {
      "type": "string",
      "description": "Pro pass key from a $5 USDC payment (optional; skips rate limits)"
    }
  },
  "required": [
    "name"
  ]
}
⚪ping_heartbeat(key, endpoints)

Record one successful run for a monitor (same as GETting https://golemreach.com/heartbeat/ping/<key>). Call this every time your job runs. For kind=selfcheck monitors pass an 'endpoints' array of {"name","status_code","cf_mitigated","tls_ms"} objects instead — alerts fire on trusted->challenged / recovery transitions only.

Eingabe-Schema

{
  "type": "object",
  "properties": {
    "key": {
      "type": "string",
      "description": "monitor key returned by create_heartbeat"
    },
    "endpoints": {
      "type": "array",
      "description": "selfcheck monitors only: one object per probed surface, e.g. {\"name\":\"claude-session\",\"status_code\":200,\"cf_mitigated\":false,\"tls_ms\":230}",
      "items": {
        "type": "object",
        "properties": {
          "name": {
            "type": "string"
          },
          "url": {
            "type": "string"
          },
          "status_code": {
            "type": "integer"
          },
          "cf_mitigated": {
            "type": "boolean"
          },
          "tls_ms": {
            "type": "integer"
          },
          "verdict": {
            "type": "string",
            "enum": [
              "trusted",
              "rate_limited",
              "error",
              "challenged"
            ]
          }
        },
        "required": [
          "name"
        ]
      }
    }
  },
  "required": [
    "key"
  ]
}
🟢record_failure(key)

Explicitly mark a run as FAILED for a monitor (same as GET https://golemreach.com/heartbeat/fail/<key>). The monitor goes DOWN immediately and alerts fire.

Eingabe-Schema

{
  "type": "object",
  "properties": {
    "key": {
      "type": "string"
    }
  },
  "required": [
    "key"
  ]
}
🟢list_heartbeats(key)

List monitors on this Heartbeat instance with current status (new/up/late/down). Names and statuses are public by design — every monitor has a public status page. Pass your secret key to also include that monitor's private ping/fail URLs in the result.

Eingabe-Schema

{
  "type": "object",
  "properties": {
    "key": {
      "type": "string",
      "description": "optional monitor key; adds the private ping_url/fail_url for that one monitor"
    }
  }
}
🟢get_status(name, key)

Full current state of one monitor: status, 30-day uptime %, schedule, last ping, alert config, recent event history and its public URLs. Look up by name OR by your secret key; key lookups additionally return the private ping/fail URLs.

Eingabe-Schema

{
  "type": "object",
  "properties": {
    "name": {
      "type": "string",
      "description": "monitor name (public lookup)"
    },
    "key": {
      "type": "string",
      "description": "monitor key (private lookup; also returns ping/fail URLs)"
    }
  }
}

Community

Diesen Server bewerten

Nachweis

Aktuelle Beobachtungen

verifiziertVersion nicht aufgezeichnet5 Tools
verifiziertVersion nicht aufgezeichnet5 Tools
verifiziertVersion nicht aufgezeichnet5 Tools