com.runvouch/runvouch

up checked 2026-11-11T10:38:42.792Z

Unclaimed · Unverified

Publisher-provided description

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

Summary by lookupd

Tracks unattended AI agent runs, raises alerts on failures or missing evidence, and issues verifiable per-run proofs.

Install

Claude Code, remote (streamable-http)

claude mcp add --transport http runvouch https://api.runvouch.com/mcp

Codex, remote (streamable-http)

codex mcp add runvouch --url https://api.runvouch.com/mcp

Cursor, remote (streamable-http) → .cursor/mcp.json

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

Other clients: docs. Or tell your agent: Set up lookupd for me: read https://lookupd.com/agent.md and follow it.

Publisher-provided text

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.p

Shows this live status and links here; updates hourly.

[![lookupd status](https://lookupd.com/badge/com.runvouch/runvouch.svg)](https://lookupd.com/servers/com.runvouch/runvouch)