Free · read-only · Chat app

Audit your Claude Desktop agents.

Audit your Claude agents for free from inside the Claude desktop app. Add the GOVENANT Audit as a custom connector and ask Claude to run a read-only, aggregate-only trust sweep of your own AI system — is it actually delivering, and can you prove it?

Add it to Claude → Read the FAQ

Step 1

Add the audit to Claude

Paste one URL — no API key. Claude Desktop connects itself.

Step 2

Sign in

GitHub or Google OAuth. That’s the whole ask.

Step 3

Ask for the audit

Say “Run a GOVENANT trust sweep.” Get a shareable report back.

Add the GOVENANT Audit to Claude Desktop

The MCP server URL:

https://mcp.govenantstandard.org/mcp

Open Settings → Customize → Connectors in the Claude desktop app.
Click "+ Add custom connector", paste the GOVENANT MCP URL, and click Add.
Click Connect — a browser opens; sign in with GitHub or Google.
In a chat, say: “Run a GOVENANT trust sweep.”

If the connector doesn’t appear, fully quit Claude (⌘Q) and reopen.

Authentication: GitHub or Google OAuth.

What the Claude Desktop audit tells you

Anomalies first

The bad news up top: motion without delivery, missed work, approvals expiring unapproved, decisions never graded — the signs of performed autonomy.

Your grade

Where your Claude agents land on the GOVENANT ladder — Logged → Gated → Delivered → Earned — and the delivery numbers behind it.

Delivery, not activity

Verified outcomes vs. total actions, work delivered vs. missed — measured against the record, never self-reported.

A shareable page

Every run has its own URL, with an optional one-click “share for a free expert review.”

Claude Desktop audit — FAQ

Does this work in Claude on the web or only the desktop app?

Custom connectors live in the Claude desktop app (macOS/Windows). Add it once there; then anyone on your team can ask Claude to run the audit.

Will Claude see my prompts or data?

No. The audit is read-only and aggregate-only — it reads summary counts and ratios from your agents’ own records, never your prompts, messages, customer data, or secrets.

Is the GOVENANT Audit really free?

Yes. You sign in with GitHub or Google so we know who ran it — that’s the whole ask. No API key, no credit card, no paywall on the audit.

What does it read, and what does it never see?

It reads aggregate numbers from your agents’ own records: how many ran, how many finished, whether checks passed, which models you use. It never reads your prompts, your agents’ messages, your customers’ data, or any secrets.

What is “performed autonomy”?

Agents that look busy — fluent plans, satisfied logs — but don’t verifiably ship. Motion is not delivery. The audit measures verified outcomes against the record, never the logs’ self-report.

Using a different tool?

ChatGPT Claude Code Cursor VS Code (Copilot)Windsurf Codex CLI Cline

Prove your agents actually deliver.

Free under the covenant — the method is free forever. Read-only and aggregate-only: your prompts, data, and secrets never leave your machine.

Add it to Claude → See it audited on itself