Arcezia / Integrations / n8n

n8n: check an AI agent action before it runs

From an n8n workflow, send the action to Arcezia’s verify endpoint before the step that performs it, and continue only on ALLOW.

Build the request

from arcezia.integrations.n8n import build_verify_body

body = build_verify_body(task="...", action_type="execute_sql",
                         action_description="...", domain=SQL)
# POST https://api.arcezia.com/v1/verify with Authorization: Bearer <key>

SQL is the contract domain from Quickstart step 4. The endpoint and its fields are in the API reference.

What you get

The response carries the verdict: ALLOW, REVIEW or BLOCK. Route the workflow on it, and let only ALLOW reach the step that acts.

On a new key a call usually comes back REVIEW first. The answer names what would release it, for example a contract for the tool or a signed scope for the session. See Handling the answers.

Same answers everywhere. Every hookup calls the same service with the same rules. Switching frameworks does not change a verdict.