Skip to main content
Glama

Arc payee check

arc_payee_check
Read-onlyIdempotent

Call this before any USDC send on Arc. We index every Arc USDC transfer: in the 7 days to 3 Nov 2026 there were 134 address-poisoning events from 50 lookalike addresses against 105 wallets (live counts: arc_poison_stats). Returns an EIP-712 signed verdict: DO_NOT_PAY / CAUTION / NO_MATCH_IN_INDEX / COULD_NOT_READ, with the address it imitates and evidence transactions; also the USDC blacklist and OFAC. 5 free checks a day per caller (no payment needed), then $0.005 over x402. Use it with PayGuard (0x942e886e4aa48346dd8bc594596f662aab57efeb on Arc) so the contract only pays on a clean, fresh verdict: pass payer and amount for that. When the verdict is NO_MATCH_IN_INDEX, that signature is an apex-upto-v1 voucher (a cap, 10 minutes, once). New boxes (arc-mandate-2, factory 0x91957bd6e6da2880bf49174eaa4b5d36627af9d3) pay only on a clean PayeeVerdict whose payer is the box. pay() uses a verdict once. x402 can reuse one unexpired verdict on each free daily slot, and the daily count still applies. Boxes from the v1 factory 0x69e444f722666e13e171181efe054a93e0976b26 do not read the verdict. The v2 factory and the v2 implementation are Sourcify exact matches. Up to 20 payees: arc_payee_batch. arc-send-guard folds the same check: DO_NOT_PAY is a stop, and the signed verdict is arc-payee-check. Our own payouts to an address a stranger chose (the X reward, jury pay, the hunter bounty, and buy-and-rate) refuse DO_NOT_PAY before USDC leaves. A first payment to a new address is still allowed.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "payee": "<payee>"
    },
    "name": "arc_payee_check"
  }
}

Input Schema

NameRequiredDescriptionDefault
payeeYesthe 0x address you are about to pay on Arc
payerNooptional: your paying wallet (catches lookalikes of YOUR real counterparties; required if you will use PayGuard)
amountNooptional: USDC amount, signed into the verdict as maxAmount (required for PayGuard)
paymentNoa signed x402 payment (the same base64 payload you would put in the PAYMENT-SIGNATURE header). Pass it here and the purchase completes inside this tool call.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.1/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly/idempotent/non-destructive, and the description still adds material the annotations cannot: the free-tier limit of 5 checks per day per caller, the $0.005 x402 charge beyond that, the fact that a verdict is single-use with pay(), the reuse rule for unexpired verdicts on free daily slots, and factory-version compatibility (v1 boxes ignore the verdict). The density and the interleaving of PayGuard/factory details make some of these traits hard to extract, which keeps it below a 5. The 'purchase completes inside this tool call' payment path is a minor tension with readOnlyHint but is framed as billing for the check, not a state mutation by the tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness2/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The one strong front-loaded sentence is followed by a run-on paragraph that mixes threat statistics, verdict taxonomy, pricing, PayGuard integration, two factory addresses, Sourcify attestations, voucher semantics, and internal payout policy. Several items (the X reward, jury pay, hunter bounty, buy-and-rate policy; the Sourcify match claim) do not help an agent decide or invoke, and key operational facts like the daily quota are buried mid-paragraph.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description carries the return contract and does so adequately: the four verdict values, the imitated address, evidence transactions, and the USDC blacklist/OFAC overlay. Given the tool's complexity (signed verdicts, pay-once semantics, paid tier), the workflow context is largely present, though the ordering and the unexplained voucher/factory references leave a few loose ends an agent must guess at.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the four parameters are already documented in the schema, including that payer and amount are required for PayGuard and that payment takes a base64 x402 payload. The description reinforces the PayGuard coupling and adds that payer catches lookalikes of your own counterparties, but supplies no new format, validation, or edge-case semantics for any parameter. Baseline 3 applies when the schema carries the load.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The opening sentence fixes both the verb and the moment of use ('Call this before any USDC send on Arc'), and the description then states exactly what the tool produces: an EIP-712 signed verdict in one of four named states, plus blacklist/OFAC data. It explicitly separates itself from siblings by naming arc_payee_batch for up to 20 payees and arc_send_guard as the folded variant, so an agent can discriminate without opening another schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives a clear trigger ('before any USDC send'), the alternative for multi-payee cases (arc_payee_batch), the wrapper alternative (arc-send-guard, where DO_NOT_PAY is a stop), and the related PayGuard path requiring payer and amount. It even carves out an exclusion ('A first payment to a new address is still allowed'), which is exactly the kind of boundary that changes agent behavior.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.