Skip to content
MCP server

runvouch

By runvouchAll Runvouch servers

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

Listed on

First seen 2 Oct 2026. One server, whatever directories list it: each directory listing keeps its own page and history.

3
Directories
1 via MCP Toplist
7
Tools
From an anonymous probe
F
ToolBench grade
Arcade’s grade, not ours
0
GitHub stars
From MCP Toplist

Tools

ToolDescriptionBehaviour
runvouch_ackAcknowledge an alert by id.Not declared
runvouch_alertsOpen (un-acknowledged) alerts: MISSED, FAILED, NO_EVIDENCE, BUDGET_RUN, BUDGET_DAY, RETRY_STORM, DRIFT, STALLED.Read-only
runvouch_run_endReport that a run ended, with status and evidence dict (name -> bool or {type:'url',url}). Green run without evidence alerts.Not declared
runvouch_run_proofTamper-evident proof of a finished run: hashed record, Merkle path, day root, chain hash and OpenTimestamps status. Verify offline with templates/verify_proof.py.Read-only
runvouch_run_startReport that a run of `agent` started. Returns run_id.Not declared
runvouch_runsRecent runs of one agent.Read-only
runvouch_statusHealth of all watched agents: state (ok/alert/failed/unproven/running/waiting), last run, 24h cost, open alerts.Read-only

Directory listings

DirectoryListingTierFirst seen
Official MCP Registrycom.runvouch/runvouch-2 Oct 2026
Smitheryrunvouch-2 Oct 2026
GlamaListed there according to MCP Toplist’s dataset; not collected by InvokeRank.