AgentAvow Documentation
Guides for checking, verifying, gating, and badging AI-agent tools.
- How scoring worksAgentAvow answers one question: is this tool safe for your agent to connect to? We point a scanner at a tool — a GitHub repo, a package (npm, PyPI, crates), a Hugging Face model, a container image, a live MCP server, or an Agent Skill — and return a signed, offline-verifiable 0–100 trust score with the findings behind it.
- Gate on the scoreA score you don't act on is trivia. AgentAvow is built so a machine can read the verdict and decide — block a risky tool, throttle an unproven one, or wave a Certified one through — in CI and at your agent's runtime. Every path below reads the same signed verdict you can recompute offline.
- Reading your scan scoreAgentAvow scans the tools, MCP servers, packages, and skills your AI agents connect to, and returns a signed 0–100 safety score you can verify yourself. This guide explains what the score means and how to read a result.
- Run locally & in CIScan your own code without sending it anywhere — same engine, same score as a hosted AgentAvow scan, but offline. Built for the inner loop and for private repos.
- Add a trust badgeShow that your tool is safe — with proof. An AgentAvow trust badge renders your repo's current signed safety score — a 0–100 number and tier word (Trusted → Blocked), coloured green→red — and clicking it opens the full, verifiable report. It's free, needs no account, and regenerates on every view, so it never goes stale.
- Verify an attestationEvery AgentAvow scan result ships with a signed attestation — a JWS (JSON Web Signature, EdDSA/Ed25519, RFC 7515) over the verdict. Anyone can verify it offline, against our published keys, without trusting our servers. That's the whole point: *not a score you take on faith — a signature you can check.*
- MCP connectorAgentAvow's remote MCP server lets Claude (and any MCP client) check whether a tool is safe before an agent connects to it. This page is for users and IT admins evaluating the connector.
- Auto-scan in Claude CodeMake "check it before you connect it" automatic. Two opt-in ways, both your own configuration. AgentAvow's MCP server never forces a scan, so nothing here can flag your setup in a directory review. You opt in; you stay in control.