90trust / 100

Runvouch

by runvouch.com in Other

MCP serverPassing, checked 8 h ago

Watchdog for unattended AI agents: alerts, evidence checks and a verifiable proof per run.

https://api.runvouch.com/mcp

Last 30 days

All checks passedSome failedAll failedNot checked
Uptime
100%
Response time
154 ms typical, 154 ms slowest 5%
Last check
8 h ago
Next check
any minute now

How to call it

Add it to any MCP client that supports remote servers.

{
  "mcpServers": {
    "runvouch": {
      "type": "http",
      "url": "https://api.runvouch.com/mcp"
    }
  }
}

7 tools

  • runvouch_status

    Health of all watched agents: state (ok/alert/failed/unproven/running/waiting), last run, 24h cost, open alerts.

  • runvouch_alerts

    Open (un-acknowledged) alerts: MISSED, FAILED, NO_EVIDENCE, BUDGET_RUN, BUDGET_DAY, RETRY_STORM, DRIFT, STALLED.

  • runvouch_ack

    Acknowledge an alert by id.

  • runvouch_runs

    Recent runs of one agent.

  • runvouch_run_start

    Report that a run of `agent` started. Returns run_id.

  • runvouch_run_end

    Report that a run ended, with status and evidence dict (name -> bool or {type:'url',url}). Green run without evidence alerts.

  • runvouch_run_proof

    Tamper-evident proof of a finished run: hashed record, Merkle path, day root, chain hash and OpenTimestamps status. Verify offline with templates/verify_proof.py.

Security scan

  • No findings. We scan names, descriptions and tool definitions for hidden instructions and other prompt-injection patterns.

Recent checks

WhenResultHTTPTime
8 h agoPassed200154 ms