Audit log

Every tool call made through mcp.clawnify.com, and every clawnify_execute run on your agent’s runtime, leaves an audit log entry. The log is per-org and append-only.

What’s captured

Each entry says when the call happened, who made it (a person, an access token, your own agent, or the platform itself), which tool it called, how long it took, and whether it failed. A code run also records its exit code, whether it timed out, and how much output it produced.

What’s NOT captured

The audit log does not record:

• The text of the code you ran (only its size).
• The stdout / stderr content (only sizes).
• The arguments you passed to a tool call (only the tool name).

If you want full request payloads, write them yourself inside your app. The platform audit is intentionally PII-light.

Export

We can ship your org’s complete audit log on request, as JSONL with one entry per line, scoped to your org. Get in touch at clawnify.com to schedule one.

Use cases

• Cost tracking. Count code runs per day to project spend.
• Anomaly detection. Watch for spikes in failed calls, or calls from a caller you don’t expect.
• Compliance. Demonstrate “who did what when” for audits.
• Debugging. Match a misbehaving agent session against the exact tool calls it made.