SafeAgent Execution Guard icon

SafeAgent Execution Guard

Durable execution-claim guard backed by the free SafeAgent test API (POST /claim/test - limited to 10 calls per IP address, total). Claims an (Agent ID, Action Type, Scope) slot before running a side-effectful action, then routes to Proceed (new) or Skip (duplicate). Call Settle after the action completes to record the result. PENDING means the external outcome is unresolved and requires reconciliation. For unlimited, paid production usage, call SafeAgent's POST /claim endpoint directly outside n8n (see github.com/azender1/SafeAgent) - this node only wires up the free tier so the package has no payment/wallet runtime dependency.

Actions2

Settle

AI-generated

Summary

Settles a previously claimed SafeAgent request by posting a JSON result with its request ID and settlement token. Returns the API response on the Proceed output.

Inputs

  • Base URL — SafeAgent API base URL; defaults to the hosted SafeAgent service. Override for a self-hosted instance.
  • Request ID (required) — The request_id returned by a previous Claim operation.
  • Settlement Token (required) — The settlement_token returned by Claim. Pass it through any side-effect node and use it here to authorize settlement.
  • Result — JSON value to store against the settled claim; defaults to an empty object.

Output shape

One item per successfully settled input, containing the SafeAgent API response, sent to the Proceed output.

Settlement errors stop execution unless Continue On Fail is enabled; then an error item is sent to Skip. A string result is parsed as JSON, and invalid JSON causes an error.

Links

Discussion