# agent_batch_audit

Paid ($4 USDC per agent on Algorand, up to 50). Every verdict for a shortlist in one call, with a summary count. The whole audit is produced before the payment is submitted, so an audit that cannot finish costs nothing. Check the total with price_quote against your cap first. Saved for 24 hours: asking again returns the saved answer and pays nothing.

Agent View of the PolicyLayer registry record for `agent_batch_audit`. HTML page: https://policylayer.com/tools/a-identity-trust-mcp/agent-batch-audit

## Facts

- Tool: `agent_batch_audit`
- Server: Trust (`@a-identity/trust-mcp`) — https://policylayer.com/tools/a-identity-trust-mcp.md
- Install: `npx -y @a-identity/trust-mcp`
- Homepage: https://www.npmjs.com/package/@a-identity/trust-mcp
- Risk category: Read (Low risk)
- Registry record: grade B, identity unverified
- Server rate-limited: no
- Parameters: 2 (1 required)
- Recommended policy verdict: Allowed

## Parameters

| Parameter | Type | Required | Description |
| --- | --- | --- | --- |
| `agentIds` | array | yes | The agents to audit. |
| `amountUsd` | number | no | What the payment you are about to make is worth, in USD. Sizes the verdict to the deal. |

Parameters from the server's own tool schema.

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "agent_batch_audit",
    "arguments": {
      "agentIds": []
    }
  }
}
```

## Why agent_batch_audit is rated Low

Even though agent_batch_audit only reads data, uncontrolled read access leaks sensitive information and racks up API costs: an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.

Risk signals: Bulk/mass operation — affects multiple targets

## Use case

AI agents call agent_batch_audit to retrieve information from Trust without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

## Recommended policy (PolicyLayer)

Verdict: **Allowed**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Trust:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "agent_batch_audit": {}
  }
}
```

## Other tools on Trust (8)

- `agent_passport` — Read — https://policylayer.com/tools/a-identity-trust-mcp/agent-passport.md
- `check_batch` — Read — https://policylayer.com/tools/a-identity-trust-mcp/check-batch.md
- `check_before_pay` — Read — https://policylayer.com/tools/a-identity-trust-mcp/check-before-pay.md
- `pay_check` — Read — https://policylayer.com/tools/a-identity-trust-mcp/pay-check.md
- `price_quote` — Read — https://policylayer.com/tools/a-identity-trust-mcp/price-quote.md
- `reputation_score` — Read — https://policylayer.com/tools/a-identity-trust-mcp/reputation-score.md
- `risk_check` — Read — https://policylayer.com/tools/a-identity-trust-mcp/risk-check.md
- `verify_agent` — Read — https://policylayer.com/tools/a-identity-trust-mcp/verify-agent.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=a-identity-trust-mcp · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/a-identity-trust-mcp
