Mmcp.market

Is Vigil — an outside witness for AI agents MCP server safe?

Probably. Read the findings first.

C56/100grade C

Use with care. Some checks failed or could not be verified.

What to know before installing
  • highWrite-action tools reachable without authentication

Public scan report

scanner v0.1.9 · 2026-09-20 · same rubric, same numbers if you re-run it

1 high1 low
  • –Code scanremote-only server, no package to scann/a
  • Live reliabilityremote reachable in 2053ms17/20
  • Tool poisoning26 tool descriptions checked15/15
  • Auth qualityopen endpoint exposes 4 write-action tools with no auth3/15
  • Maintenanceno repository listed3/15
  • Maintainer identityverified namespace with website, no repo4/10

Findings (2)

  • highWrite-action tools reachable without authenticationauth.open-write
  • lowNo source repository listedmaint.no-repo
Overall 56/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

Other servers that do what Vigil — an outside witness for AI agents does

  • Protect
    Fail-closed Cedar policy gate + Ed25519 signed receipts for agent tool calls. Denies on any error.
    C
  • Ausca
    Pay-per-call APIs and MCP services for agents, no accounts or keys, with verifiable receipts.
    B
  • HOL Guard
    Local-first AI agent security evidence and approval workflows through HOL Guard's stdio MCP server.
    A

Vigil — an outside witness for AI agents reviews, tools and install