Public
Free
Certify open-source skills and MCP servers, verify any certificate with the open CLI, and browse the public ledger. No account needed.
Product · trust.workrr.ai
Certify the skills your AI agents run.
Every skill, MCP server, and ruleset an agent loads runs with the agent's access. Trust gives each one a neutral, signed certificate, recorded in a public transparency log and checkable by anyone, on any agent platform. You don't have to trust us. You can verify it.
Certify, verify, gate.
On the formats your agents already use: AGENTS.md, CLAUDE.md, MCP, A2A, and SKILL.md.
- CertifyOpen-source certifier code checks provenance and policy, scans for known injection patterns, and runs a reproducible test suite.
- VerifyEvery certificate and revocation goes into a public, append-only log. Anyone can re-run the tests and get the same result.
- GateAgents resolve against a private registry of certified, version-pinned artifacts. Nothing uncertified loads.
- AuditRevocation is instant, and every decision is on record for your auditors.
- OpenCertificates come from an open-source workflow pinned to an exact commit. No hidden allowlist.
- IndependentSigned with Sigstore and logged in its public Rekor log. Gold certificates need two independent forges to agree.
- PrivateFor internal artifacts, the certifier runs in your own CI. Only a hash goes in the public log.
Free in public. Paid in private.
Publisher
Per publisher
For companies shipping MCP servers, skills, or agent integrations. Gold certification, recertified on every release, with a verified publisher badge.
Private · Team and enterprise
Talk to us
Private certificates and registry, policy authoring, and an audit trail, with a hands-on rollout from our engineers.
Running agents on internal artifacts?
We help your team set up certification in your own CI, stand up the private registry, and write the policies, so your engineers own the process.