# Trust MCP server

Agent View of the PolicyLayer registry record for Trust: identity, probed posture, risk grade, and all 9 tools classified. HTML page: https://policylayer.com/tools/a-identity-trust-mcp

## Facts

- Server id: `@a-identity/trust-mcp`
- Install: `npx -y @a-identity/trust-mcp`
- Homepage: https://www.npmjs.com/package/@a-identity/trust-mcp
- Registry record: grade B, identity unverified
- Lifecycle: active
- Rate-limited: no
- Tools: 9 (9 with introspected schema)
- Tool categories present: Read
- Context-window cost: 1652 tokens per request — https://policylayer.com/token-cost/a-identity-trust-mcp
- Tags: a identity trust mcp
- Record last modified: 2026-10-15T19:26:51.691Z

## Tools (9)

| Tool | Category | Risk | Record |
| --- | --- | --- | --- |
| `agent_batch_audit` | Read | Low | https://policylayer.com/tools/a-identity-trust-mcp/agent-batch-audit.md |
| `agent_passport` | Read | Low | https://policylayer.com/tools/a-identity-trust-mcp/agent-passport.md |
| `check_batch` | Read | Low | https://policylayer.com/tools/a-identity-trust-mcp/check-batch.md |
| `check_before_pay` | Read | Low | https://policylayer.com/tools/a-identity-trust-mcp/check-before-pay.md |
| `pay_check` | Read | Low | https://policylayer.com/tools/a-identity-trust-mcp/pay-check.md |
| `price_quote` | Read | Low | https://policylayer.com/tools/a-identity-trust-mcp/price-quote.md |
| `reputation_score` | Read | Low | https://policylayer.com/tools/a-identity-trust-mcp/reputation-score.md |
| `risk_check` | Read | Low | https://policylayer.com/tools/a-identity-trust-mcp/risk-check.md |
| `verify_agent` | Read | Low | https://policylayer.com/tools/a-identity-trust-mcp/verify-agent.md |

## Tool descriptions

- `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 w…
- `agent_passport` — Paid ($10 USDC on Algorand). Identity, KYA, reputation and the risk verdict for one agent in a single document. Saved for 24 hours: asking again returns the saved answer and pays nothing.
- `check_batch` — check_before_pay for up to 20 targets at once, each with the amount you would pay it. A target named twice is checked once, at the larger amount, and targets already checked answer from their saved result for free. Do not pay a target wh…
- `check_before_pay` — Call this BEFORE every payment you make. Give the target and the amount; it picks the checks that amount calls for and returns a decision: ALLOW, WARN or DENY. An Algorand address or x402 seller gets "is it safe to pay" ($5). An agent ge…
- `pay_check` — Paid ($5 USDC on Algorand). Before paying an Algorand address: Looks safe, Be careful or Don't pay, with the reasons, its biggest payers (and whether they are linked to it), its last payments, and the wallet that created it. Takes an Alg…
- `price_quote` — Free. The live price of one A-Identity trust tool in USDC on Algorand, read from its x402 challenge. For agent_batch_audit, pass count to price a shortlist.
- `reputation_score` — Paid ($2 USDC on Algorand). A deterministic 0-1000 reputation with its breakdown, a Sybil signal, and the latest on-chain attestation of the score. Saved for 24 hours: asking again returns the saved answer and pays nothing.
- `risk_check` — Paid ($5 USDC on Algorand). Call BEFORE paying or hiring another agent: an ALLOW / WARN / DENY verdict on the counterparty with the reasons and signals behind it. Do not pay on DENY. Prefer check_before_pay. Saved for 24 hours: asking ag…
- `verify_agent` — Paid ($1 USDC on Algorand). Whether the agent has an on-chain ERC-8004 identity, its KYA (Know Your Agent) status, and whether it has been revoked. Saved for 24 hours: asking again returns the saved answer and pays nothing.

## 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 · Recommended policies for every tool: https://policylayer.com/policies/a-identity-trust-mcp
