---
title: "AI agent decision pre-flight: GO / CAUTION / STOP with cryptographic receipt."
method: POST
path: "/v2/agent_preflight"
tags: ["agent-safety"]
---

# AI agent decision pre-flight: GO / CAUTION / STOP with cryptographic receipt.

`POST /v2/agent_preflight`

AI agent decision pre-flight + action audit + autonomous safety — should agent X execute action Y? Combined check: evidence freshness, provenance trace, policy gate, risk scoring, hallucination signals. Returns GO / CAUTION / STOP / INSUFFICIENT_EVIDENCE with cryptographic receipt. For autonomous agent workflows: tool calls, financial transactions, content publishing, regulatory submissions, multi-step task execution, agent compliance evidence, MCP gateway routing.

## Request body

- object
  - `intent` string, required — Description of what the agent wants to do
  - `context` object — Optional agent context (agent_id, session_id, etc.)

## Response `200`

Success (synthetic example)

## Other responses

- `400` — Bad Request — invalid or missing parameters.
- `402` — Payment Required (x402): response carries payment requirements; retry with the X-PAYMENT header (USDC on Base).

---

[API](https://skmtc.net/tooloracle/apis/tooloracle-mcp-platform.md) · [All operations](https://skmtc.net/tooloracle/apis/tooloracle-mcp-platform/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/tooloracle/tooloracle-mcp-platform/versions/0f85b83186f5/schema)