
Official MCP RegistryListed
PayStage — x402 payment safety
x402 payment safety: stop your agent paying a drainer before the wallet signs.
First seen 12 Nov 2026. Evidence as of 22 Nov 2026.
10
Tools
From an anonymous probe
1
Source listings
Each with its own history
50
Recorded changes
Since first seen
Tools
| Tool | Description | Behaviour |
|---|---|---|
| decode_payment_required | verify the recipient. Call this first when a 402 response arrives and you cannot read the payment-required header. Returns the decoded x402 v2 challenge: scheme, network, asset, atomic amount, payee, resource and timeout. Pure decoding: no network call, no signature, no verdict — use evaluate_mcp_payment when you want a decision. Fails closed with a named error if the header is malformed or not base64. Fails closed: do not invent authority — a missing policy, identity, cost or evidence is a refusal, never a default. | Read-only |
| evaluate_batch | transaction scope. Call this when an agent might pay several times in one turn and you want one policy decision covering all of them. Verdict is pay | review | do_not_pay per item, in input order, with reason codes — so the agent can stop at the first refusal rather than discovering it after three payments. Read-only, holds no keys, never signs. Cheaper and more consistent than calling evaluate_mcp_payment in a loop: same policy, one round trip. Fails closed: do not invent authority — a missing policy, identity, cost or evidence is a refusal, never a default. | Read-only |
| evaluate_hip3_trade | transaction scope. Call this BEFORE an agent places a HIP-3 / trade.xyz order. Verdict is allow | review | do_not_trade, with the rule that fired (notional above cap, market not allowed, leverage too high). Returns the decision and a one-line reason. Local policy only: this is not financial advice, holds no keys, and cannot place or cancel an order. Prices come from a read-only market query. Fails closed: do not invent authority — a missing policy, identity, cost or evidence is a refusal, never a default. | Read-only |
| evaluate_mcp_payment | verify the recipient. Call this BEFORE signing any x402 payment. Verdict is pay | review | do_not_pay, each with stable reason codes (e.g. 'amount 1.00 USDC exceeds max_amount 0.05 USDC'). Fail-closed by design: do not invent authority — when policy, identity, cost or evidence is missing the answer is a refusal or a review, never a pay. A `review` verdict also carries a `packet` object with the amount and its share of the applicable cap, the payee, the rule that fired, the checks run and skipped, and the one decision being asked of the human; `pay` and `do_not_pay` do not. Returns the decision plus a signed receipt you can verify offline with verify_receipt, and a `bundle_id` naming the evidence bundle for this call (events, hashed inputs, receipt, summary). Read-only: holds no keys, never signs, never moves funds. A refusal costs nothing. This tool evaluates locally, so it makes no network calls and returns no seller reputation; the hosted HTTP API adds `seller_reputation` (domain and certificate age) because it can reach the network. | Read-only |
| evaluate_outstanding_auths | spending limits. Call this when an agent already holds authorisations and you need to know which are dangerous. Verdict is pay | review | do_not_pay per authorisation, with reason codes naming the rule that fired (unlimited allowance, expiry already passed, spender not on the allow-list). Returns per-authorisation decisions plus a summary action. Read-only: never revokes, never signs. Revocation is a transaction you send yourself. Fails closed: do not invent authority — a missing policy, identity, cost or evidence is a refusal, never a default. | Read-only |
| evaluate_velocity | transparent risk assessments. Call this when an agent is about to make its Nth payment and you need to know whether the rate itself is the risk. Verdict is pay | review | do_not_pay over a rolling window (per-hour and per-day spend, count of payees). Returns the decision plus which window was breached. Read-only: it reads the history you pass in, holds no keys, and calls no external service. Fails closed: do not invent authority — a missing policy, identity, cost or evidence is a refusal, never a default. | Read-only |
| list_outstanding_auths | spending limits. Call this when auditing what an agent could still spend without a new signature — ERC-20 allowances, Permit2 and EIP-3009 authorisations. Returns each authorisation with spender, amount and expiry. Read-only and needs only a public RPC; no key, no funds moved. Use it after an incident to see what remains exposed, not to revoke anything (this tool cannot revoke). Fails closed: do not invent authority — a missing policy, identity, cost or evidence is a refusal, never a default. | Read-only |
| request_testnet_funds | test funds. Call this when you need Base Sepolia USDC to exercise the paid path end to end — one drip of 0.5 USDC per address per 24 hours, and the refusal tells you when it resets rather than just failing. Reads a public faucet: no key needed, no account, and it can only ever send testnet USDC. Use a throwaway address for anything automated; the cap is per address, so a script that generates a new address per call is not clever, it is why faucets get closed. Fails closed: do not invent authority — a missing policy, identity, cost or evidence is a refusal, never a default. | Changes data |
| validate_policy | spending limits. Call this before wiring a policy into anything: a policy that fails validation makes every evaluation refuse, which looks like a product bug and is not one. Returns valid: true, or the exact field and message that is wrong. No payment needed, no network call, no key. Use it in CI on the policy file your agent ships with. Fails closed: do not invent authority — a missing policy, identity, cost or evidence is a refusal, never a default. | Read-only |
| verify_receipt | verify the recipient. Call this when you have a receipt and want to know whether it is genuine, without trusting the server that issued it. Returns VALID with the verdict it attests to, INVALID if the payload was altered, or UNVERIFIABLE when the key cannot be fetched — and UNVERIFIABLE is a refusal, not a pass. Pass `chain` instead of one receipt to walk a hash-chained list: it verifies every link and reports the first gap by index, with the receipt ids either side. Needs only the receipt JSON and a network connection; no account, no shared secret. Fetches the signing key from a published URL you can pin with key_url. Fails closed: do not invent authority — a missing policy, identity, cost or evidence is a refusal, never a default. | Read-only |
Change history
- evaluate_mcp_payment: description changed (+"verify_receipt, and a `bundle_id` naming the evidence bundle for this call (events, hashed inputs, receipt, summary)." -"verify_receipt.")
- verify_receipt: input schema changed (+chain)
- verify_receipt: description changed (+"Pass `chain` instead of one receipt to walk a hash-chained list: it verifies every link and reports the first gap by index, with the receipt ids either side.")
- evaluate_mcp_payment: description changed (+"A `review` verdict also carries a `packet` object with the amount and its share of the applicable cap, the payee, the rule that fired, the checks run and skipped, and the one decision being asked of the human; `pay` and `do_not_pay` do not.")
- verify_receipt: description changed (+"Fails closed: do not invent authority — a missing policy, identity, cost or evidence is a refusal, never a default.")
- validate_policy: description changed (+"Fails closed: do not invent authority — a missing policy, identity, cost or evidence is a refusal, never a default.")
- request_testnet_funds: description changed (+"Fails closed: do not invent authority — a missing policy, identity, cost or evidence is a refusal, never a default.")
- list_outstanding_auths: description changed (+"Fails closed: do not invent authority — a missing policy, identity, cost or evidence is a refusal, never a default.")
- evaluate_velocity: description changed (+"Fails closed: do not invent authority — a missing policy, identity, cost or evidence is a refusal, never a default.")
- evaluate_outstanding_auths: description changed (+"Fails closed: do not invent authority — a missing policy, identity, cost or evidence is a refusal, never a default.")
- evaluate_mcp_payment: input schema changed (+payment_identifier)
- evaluate_mcp_payment: description changed (+"Fail-closed by design: do not invent authority — when policy, identity, cost or evidence is missing the answer is a refusal or a review, never a pay.")
- evaluate_hip3_trade: description changed (+"Fails closed: do not invent authority — a missing policy, identity, cost or evidence is a refusal, never a default.")
- evaluate_batch: description changed (+"Fails closed: do not invent authority — a missing policy, identity, cost or evidence is a refusal, never a default.")
- decode_payment_required: description changed (+"Fails closed: do not invent authority — a missing policy, identity, cost or evidence is a refusal, never a default.")
- evaluate_velocity: input schema changed
- evaluate_mcp_payment: description changed (+"This tool evaluates locally, so it makes no network calls and returns no seller reputation; the hosted HTTP API adds `seller_reputation` (domain and certificate age) because it can reach the network.")
- verify_receipt: description changed (+"verify the recipient.")
- validate_policy: description changed (+"spending limits.")
- request_testnet_funds: tool added
- list_outstanding_auths: description changed (+"spending limits.")
- evaluate_velocity: description changed (+"transparent risk assessments.")
- evaluate_outstanding_auths: description changed (+"spending limits.")
- evaluate_mcp_payment: description changed (+"verify the recipient.")
- evaluate_hip3_trade: description changed (+"transaction scope.")
- evaluate_batch: description changed (+"transaction scope.")
- decode_payment_required: description changed (+"verify the recipient.")
- verify_receipt: description changed (+"Call this when you have" +"and want to know whether it is genuine, without trusting" +"server that issued it.")
- validate_policy: description changed (+"Call this before wiring a policy into anything:" +"that fails validation makes every evaluation refuse, which looks like" +"product bug and is not one.")
- list_outstanding_auths: description changed (+"Call this when auditing what an agent could still spend without a new signature — ERC-20 allowances, Permit2 and EIP-3009 authorisations. Returns each authorisation with spender, amount and expiry. Read-only and needs only" +"public RPC; no key, no funds moved. Use it after an incident to see what remains exposed, not to revoke anything (this tool cannot revoke)." -"List outstanding token authorizations for")
- evaluate_velocity: description changed (+"Call this when an agent is about to make its Nth payment and you need to know whether the" +"itself is the risk. Verdict is pay | review | do_not_pay over a rolling window (per-hour" +"per-day spend, count of payees). Returns the decision plus which window was breached. Read-only: it reads the")
- evaluate_outstanding_auths: description changed (+"Call this when an agent already holds authorisations" +"you need to know which are dangerous. Verdict is pay | review | do_not_pay per authorisation, with reason codes naming the rule that fired (unlimited allowance, expiry already passed, spender not on the allow-list). Returns per-authorisation decisions plus a summary action. Read-only: never revokes, never signs. Revocation is" +"transaction you send yourself.")
- evaluate_mcp_payment: description changed (+"Call this BEFORE signing any" +"payment. Verdict is pay | review | do_not_pay, each with stable reason codes (e.g. 'amount 1.00 USDC exceeds max_amount 0.05 USDC'). Returns the decision plus" +"signed receipt you can verify offline with verify_receipt. Read-only: holds no keys, never signs, never moves funds. A refusal costs nothing.")
- evaluate_hip3_trade: description changed (+"Call this BEFORE an agent places" +"/ trade.xyz order. Verdict is" +"do_not_trade, with the rule that fired (notional above cap, market not allowed, leverage too high). Returns the decision and a one-line reason. Local policy only: this is not financial advice, holds no keys, and cannot place or cancel an order. Prices come from a read-only market query.")
- evaluate_batch: description changed (+"Call this when an agent might pay" +"times in one turn and you want" +"decision covering all of them. Verdict is pay | review | do_not_pay")
- decode_payment_required: description changed (+"Call this first when" +"arrives and you cannot read the payment-required header. Returns the decoded x402 v2 challenge: scheme, network, asset, atomic amount, payee, resource and timeout. Pure decoding: no network call, no signature, no verdict — use evaluate_mcp_payment when you want a decision. Fails closed with a named error if" +"header is malformed or not base64.")
- Name changed from "PayStage" to "PayStage — x402 payment safety" (registry)
- Description changed (registry)
- verify_receipt: tool added
- validate_policy: tool added
- list_outstanding_auths: tool added
- evaluate_velocity: tool added
- evaluate_outstanding_auths: tool added
- evaluate_mcp_payment: input schema changed (+agent_id, +policy_path)
- evaluate_mcp_payment: description changed (+"Evaluate" +"PaymentRequired payload" +"PayStage spending policy before paying")
- evaluate_mcp_payment: annotations changed
- evaluate_hip3_trade: tool added
- evaluate_batch: tool added
- decode_payment_required: tool added
- MCP URL changed (registry)
| Source | Listing | First seen | Last seen | Versions |
|---|---|---|---|---|
| Official MCP Registry | io.github.base-buzz/mcp | 12 Nov 2026 | 22 Nov 2026 | 3 |