
PayStage — x402 payment safety and spend policy
Read-only payment preflight that returns pay, review or do-not-pay before an agent signs
Answered our latest tool-list check 5 hours ago with 10 tools. It will be marked verified after 3 successful checks in 7 days.
- Pricing
- Open source
- Platforms
- API, CLI, self-hosted
- Runs
- Locally or Remotely
- Version
- 0.8.15
- Listing updated
- today
Similar MCP servers
About PayStage — x402 payment safety and spend policy
PayStage — x402 payment safety and spend policy is an open-source MCP server for finance and payments. It can run locally on your machine or as a hosted remote server.
The README describes PayStage as an MCP server for checking an agent's payment before it is signed, using a local policy file for spend caps, allowlists and payee checks. Its verdicts are pay, review or do_not_pay, and a refusal names the rule that fired. The server holds no keys and never signs, so the agent remains the only signer.
Beyond x402 payments, the package also covers outstanding ERC-20, Permit2 and EIP-3009 authorisations, velocity checks for bursts and runaway spend, HIP-3 trade order preflight, and verification of signed receipts. A policy can be validated offline with a separate command before it is used.
The project is aimed at developers building agents that make paid HTTP or MCP calls on Base, who want a policy gate outside the wallet. A hosted endpoint at api.paystage.xyz offers the same evaluation over plain HTTP for those who prefer not to install anything.
Install
Run in a terminal
claude mcp add --transport http x402-payment-safety https://api.paystage.xyz/mcpAdd to Settings → Connectors → Add custom connector
https://api.paystage.xyz/mcpAdd to ~/.cursor/mcp.json
{
"mcpServers": {
"x402-payment-safety": {
"url": "https://api.paystage.xyz/mcp"
}
}
}Add to .vscode/mcp.json
{
"servers": {
"x402-payment-safety": {
"type": "http",
"url": "https://api.paystage.xyz/mcp"
}
}
}Add to ~/.codeium/windsurf/mcp_config.json
{
"mcpServers": {
"x402-payment-safety": {
"serverUrl": "https://api.paystage.xyz/mcp"
}
}
}Add to Grok Bot desktop app → Connect apps → Add a custom connector
https://api.paystage.xyz/mcpEnter a Name (for example "PayStage — x402 payment safety and spend policy"), choose Type: Remote HTTPS, paste this as the Server URL and choose Add plugin.
Add to your client's MCP settings (most use this shape)
{
"mcpServers": {
"x402-payment-safety": {
"type": "http",
"url": "https://api.paystage.xyz/mcp"
}
}
}Using several servers? Build one config file with the MCP config generator.
Configuration
PAYSTAGE_POLICY_PATHPath to policy.json spending rulesPAYSTAGE_RPC_URLBase RPC URL override
Tools this server provides (10)
Read directly from the server.
9 of 10 tools say they're read-only. 1 of 10 tools says it can delete or change data.
From the server's own tool annotations; not verified by us.
- evaluate_mcp_paymentSays read-only
- 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'). Returns the decision plus a signed receipt you can verify offline with verify_receipt. Read-only: holds no keys, never signs, never moves funds. A refusal costs nothing.
- list_outstanding_authsSays read-only
- 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).
- evaluate_outstanding_authsSays read-only
- 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 i
- evaluate_hip3_tradeSays read-only
- 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.
- evaluate_velocitySays read-only
- 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.
- verify_receiptSays read-only
- 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. Needs only the receipt JSON and a network connection; no account, no shared secret. Fe
- decode_payment_requiredSays read-only
- 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 ba
- validate_policySays read-only
- 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.
- request_testnet_fundsSays it can change data
- 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 ne
- evaluate_batchSays read-only
- 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_mc
What it does
- Pre-signature payment verdicts
- Evaluates a proposed x402 payment and returns pay, review or do_not_pay with the rule that triggered the result.
- Local policy file
- Spending caps, allowed networks and unknown-payee handling are set in a policy.json read by the server.
- Authorisation monitoring
- Lists and flags outstanding ERC-20, Permit2 and EIP-3009 authorisations that have not settled.
- Velocity checks
- Flags bursts, spikes and runaway spend cadence over recent action history.
- Signed receipt verification
- Checks a receipt against the published signing key and reports whether it is valid, altered or expired.
- Batch evaluation
- Evaluates several payments in input order, one verdict each, so a batch stops at the first refusal.
Good for
- Checking the payee of an x402 API call before an agent signs the payment
- Limiting an agent's per-payment and cumulative USDC spend with a policy file
- Reviewing outstanding token authorisations before making another payment
- Validating a policy document in CI before shipping an agent with it
- Decoding a 402 payment-required header to inspect its challenge before paying
Pricing
Open source
MIT-licensed packages are free to run locally; hosted API free for the first 1,000 evaluations per IP per day, then $0.002 USDC per call.
Prices change. Check paystage.xyz before you buy.
PayStage — x402 payment safety and spend policy FAQ
Does the server hold keys or sign transactions?
No. The README and website state that it is read-only, holds no keys and never signs; the agent remains the only signer.
How is it installed?
The README gives the command npx -y -p @paystage/mcp paystage-mcp, and an MCP configuration that sets PAYSTAGE_POLICY_PATH to a policy file.
What environment variables does it use?
PAYSTAGE_POLICY_PATH for the spending rules file and PAYSTAGE_RPC_URL for a Base RPC override, both optional.
What does a hosted call cost?
The website says the first 1,000 evaluations per IP per day are free with no account, and calls beyond that cost $0.002 USDC per call over x402.
Is PayStage — x402 payment safety and spend policy free?
Yes. PayStage — x402 payment safety and spend policy is open source, so you can use and self-host it for free.
How do I add PayStage — x402 payment safety and spend policy to Claude Code?
Run this command in your terminal: claude mcp add --transport http x402-payment-safety https://api.paystage.xyz/mcp
What are the best alternatives to PayStage — x402 payment safety and spend policy?
The closest alternatives to PayStage — x402 payment safety and spend policy are PayStage x402 Guard — payment safety before the wallet signs, PayStage Preflight, PayStage Preflight, PayStage and PayStage.
Where this comes from
- Description: written from the project's README, the project's website and its MCP Registry entry.
- Status and tools: checked automatically by AIPoweredBot on 19 November 2026.
- Install steps: from the official MCP Registry entry.