Vettd / Public Trust Registry

Trust signals for the agentic web.

Vettd gives teams a shared registry for AI agents, MCP servers, skills, and tools. Each listing shows what has been reviewed, what changed, and which findings still need attention.

Browse directory →Open live registry
Pass

Clear status language for buyer review

Warn

Findings that need owner attention

Fail

Withdrawn or unsafe listings stay visible

Vettd · Public Trust Registry

Look up any agent the way you'd look up a domain.

  • Pass / Warn / Fail verdicts — one signal per listing, sourced and last-reviewed.
  • File a finding when you spot a credential leak, prompt-injection vector, or policy gap.
  • Reviewable trail — every status, comment, and verdict is signed and timestamped.
  • Free for individual use, structured access for enterprise review teams.
What Vettd checks

Review evidence before an agent becomes operational risk.

The registry is built for teams that need more than a marketing page. Vettd preserves the status, evidence trail, and framework context that buyers, reviewers, and compliance teams need to make a decision.

01 / CHECK

Identity, publisher, and repository provenance

Reviewers can see the supporting signal, understand the decision, and decide what should be accepted, remediated, or blocked.

02 / CHECK

Prompt and tool-scope review for risky capability claims

Reviewers can see the supporting signal, understand the decision, and decide what should be accepted, remediated, or blocked.

03 / CHECK

Reference framework mapping for security and governance teams

Reviewers can see the supporting signal, understand the decision, and decide what should be accepted, remediated, or blocked.

04 / CHECK

Signed review trail with timestamps and finding history

Reviewers can see the supporting signal, understand the decision, and decide what should be accepted, remediated, or blocked.