For developers

Ship a tool your users can trust — and prove it.

A signed, offline-recomputable safety score for the MCP server, package, or agent tool you publish. Free, no account. Claim it, put its badge on your README, or check a private repo first.

1 · Claim your tool

Prove it's yours

A claimed tool shows a “✓ Maintainer-claimed” chip on its result, and we watch it for you: you get an alert when its answer or score changes.

  1. Sign in and paste owner/repo.
  2. Add the GitHub topic we give you, agentavow-verify-…, or run gh repo edit owner/repo --add-topic agentavow-verify-…
  3. Press Verify topic. We start watching it for you.
YESPublic GitHub repos and skills: the GitHub topicYESnpm, PyPI, crates: automatic when the package links to a repo you've claimed, or a keyword you publishYESMCP servers: return the code in an X-AgentAvow-Verify header or serverInfo, or serve /.well-known/owners.json listing your verified account email
2 · Get your badge

Put the answer on your README

One line of Markdown. It shows the current signed answer, trust score and adoption, and links to the full report. No account needed for a public tool.

Example AgentAvow badge[![AgentAvow](https://agentavow.com/api/v1/public/scan/you/your-repo/badge)](https://agentavow.com/check/you/your-repo)
YESGitHub repos, npm, PyPI and crates packages, and MCP servers
3 · Check a private repo

Check it before it's public

Two ways. Both need you signed in.

  1. GitHub App. Install it on the repos you choose. We check them now and re-check daily.
  2. One-time token. A fine-grained, read-only token for a single check. It's used for that check and never stored.

What you get: a private report only you can open. It isn't listed in Browse or search, and it has no public badge. To get a badge, publish the result: publishing lists it in Browse and turns the badge on.

YESA private report (GitHub App: kept and re-checked daily; token: one check, nothing kept)YES"Publish to search" for GitHub App repos, which also turns on the badge

Your badge, your way.

The badge regenerates on every view, so it never goes stale in your README, and clicking it opens the full signed report. Pick a style, copy one line.

Style
One line, both meters: the answer, trust score and adoption.
Example:Example AgentAvow badge
[![AgentAvow](https://agentavow.com/api/v1/public/scan/you/your-repo/badge)](https://agentavow.com/check/you/your-repo)

More styles and themes: Badge docs →

Or embed the live widget

The trust card (the answer, the trust bar and the adoption dial), linked to the report, plus a Verify offline button that checks the Ed25519 signature in your reader's own browser. One script tag, no tracking.

<script src="https://agentavow.com/widget.js"
        data-tool="you/your-repo"></script>
Live preview

Enter a repo or package to preview the live widget.

Not listed yet? Add it.

Pasting a link into Check is the fastest way to see an answer, and a GitHub repo or an npm, PyPI, crates, Docker or Hugging Face package you check there joins the public catalog on its own. A live MCP server checked by URL doesn't. Add it here: we scan it, sign the result and list it in Browse. Free, no account.

Try:

Why put a score on your tool.

It works because it's the one score a skeptic can check for themselves.

Signed, not "trust us"

Every score is signed (Ed25519), so anyone can prove who issued it, when, and that nobody changed the number in your README. They verify it offline against our public keys.

Stand out in a crowded space

MCP servers and agent tools are multiplying. A signed high score is a trust signal to your users for a new project nobody has vetted yet.

One score, everywhere your code lives

MCP server, npm, PyPI, GitHub repo, or skill: one recomputable score across all of them, that travels with the artifact.

Actionable, not a black box

Score poorly and the report points at the exact file and line, with the fix. Score well and you get the badge.

Gate pull requests and agents on the answer.

For a public repo, the hosted GitHub Action comments the answer and the trust score on every PR, and fails the build when the answer is Do not connect. When the repo publishes a package, AgentAvow also runs it in the behavioral sandbox and the Action prints a Sandbox: line; fail_on_behavioral: true fails the build on a high or critical sandbox finding. Prefer to keep it all local? agentavow scan . runs offline, and nothing leaves your machine.

- uses: AgentAvow/AgentAvow/github-action@main
  with:
    fail_on: do_not_connect   # the default; "review" is stricter
    fail_on_behavioral: true
Other places to gate

Carry the score into the MCP Registry.

The signed block rides the publisher-provided _meta slot into your registry record. It is offline-recomputable, so a reviewer checks it without trusting us. Live block: /api/v1/public/registry-snippet/you/your-repo

"_meta": {
  "io.modelcontextprotocol.registry/publisher-provided": {
    "com.agentavow/trust": {
      "trustScore": 92,
      "certified": false,
      "subject": "github:you/your-repo",
      "issuer": "did:web:agentgraph.co",
      "attestation": "<signed JWS — recompute & verify offline>",
      "jwks": "https://agentgraph.co/.well-known/jwks.json"
    }
  }
}
For anyone running an agent

Give your agent a safety check before it connects anything.

Add AgentAvow's own MCP server to Claude, ChatGPT, Cursor, or any MCP client. Your agent can ask "is this tool safe to install?" and get a signed 0-100 score and findings back, before it connects an unknown server or runs a package. Free, no account, read-only.

Claude Code: claude mcp add agentavow-trust -- uvx agentavow-trust

Or install the Claude Code plugin, which also checks each new MCP server at session start and warns you before your agent uses one: /plugin marketplace add AgentAvow/AgentAvow then /plugin install agentavow-trust@agentavow. How it works.

The plugin's checks run on your machine, so they cost Claude nothing: zero tokens per check, under 1,000 a session. The numbers.

{
  "mcpServers": {
    "agentavow-trust": {
      "command": "uvx",
      "args": [
        "agentavow-trust"
      ]
    }
  }
}

Prefer the terminal? npx agentavow-trust scan owner/repo gives a signed score from the command line, no install.