# Boundary Guard Agent Handoff

> Boundary Guard Agent Handoff is a paid API for AI agents from boundary-guard-x402.onrender.com, paid per call via x402, $0.01/call, status unknown (last checked 2026-09-15).

Validates, risk-scans, and authorizes an inter-agent handoff by checking payload safety, extracting structured data, redacting PII, and issuing a cryptographic Boundary Receipt with a routing decision.

## Facts

- Endpoint: POST https://boundary-guard-x402.onrender.com/agent-handoff
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/boundary-guard-agent-handoff-07581cf8
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_yqOlMS2zJJpMpMzRxVSjU

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability boundary-guard-agent-handoff-07581cf8 -d '<json body>'
```

Example prompt: Before handing off this wallet funding task to the coinbase:wallet-agent, run a Boundary Guard risk scan and get an Agent Handoff Receipt — the task is: 'Prepare a wallet funding request, but do not broadcast anything yet', coming from virtuals:researcher.alice, and validate it against my task schema.

## When to prefer this

Use this endpoint when an AI agent needs to safely hand off a task to another agent in a multi-agent pipeline and requires runtime trust enforcement: risk scanning, PII redaction, schema normalization, and an auditable cryptographic receipt. Prefer this over simple forwarding when compliance, auditability, or safety guardrails around sensitive tasks (e.g. financial operations) are required.

## Known failure modes

- Missing required 'data' or 'schema' fields returns a 400 validation error
- Payment not included or invalid results in 402 Payment Required
- Schema mismatch between provided data and schema causes normalization failure
- High risk score results in decision='deny' with reasons listed
- Service unavailable on Render free tier causes cold-start delays or 503 errors

## Output

Returns a structured JSON object containing: a risk score with any flagged issues, an allow/deny decision, a sanitized version of the task, a cryptographic Boundary Receipt with receipt_id and SHA256 hashes, agent routing info (to/from agent identifiers), per-check results (e.g. risk.scan pass/fail), retryability flag, and a recommended_action such as 'proceed_with_handoff'.

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/boundary-guard-agent-handoff-07581cf8/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from boundary-guard-x402.onrender.com](https://www.zero.xyz/host/boundary-guard-x402.onrender.com/llms.txt)