{"$schema":"https://verifymcp.io/schemas/trust-report.json","schemaVersion":1,"license":{"name":"CC BY-NC 4.0","url":"https://creativecommons.org/licenses/by-nc/4.0/"},"generatedAt":"2026-11-21T23:24:47.766Z","url":"https://verifymcp.io/servers/base-buzz-x402-payment-safety/paystage-mcp","markdownUrl":"https://verifymcp.io/servers/base-buzz-x402-payment-safety/paystage-mcp.md","server":{"slug":"base-buzz-x402-payment-safety","name":"PayStage — x402 payment safety and spend policy","registryName":"io.github.base-buzz/x402-payment-safety","description":"x402 payment safety: judge a payment against your policy before signing. No keys, never signs.","registryStatus":"active","deletedAt":null,"statusMessage":null,"liveness":"live","publisher":{"class":"unknown","claimed":false}},"component":{"slug":"paystage-mcp","type":"npm","identifier":"@paystage/mcp","withdrawn":false,"url":"https://verifymcp.io/servers/base-buzz-x402-payment-safety/paystage-mcp","version":"0.8.17","transport":"stdio","scoredAt":"2026-11-21T00:07:27.885Z"},"score":{"total":78,"tier":"medium","status":"scored","weekDelta":null,"history":[{"date":"2026-11-21","total":78},{"date":"2026-11-20","total":62},{"date":"2026-11-19","total":77},{"date":"2026-11-18","total":62}]},"categories":[{"name":"Supply Chain Security","score":100,"verdict":"pass","reasons":["No malware found by supply-chain analysis.","No known CVEs affecting this package version or its production dependencies.","No install/post-install scripts declared.","0 of 9 dependencies flagged as unhealthy."],"codes":[{"code":"supplychain.malware_clean","args":{}},{"code":"cve.none","args":{}},{"code":"installscript.none","args":{}},{"code":"dephealth.assessed","args":{"deps":"9","unhealthy":"0"}}]},{"name":"Provenance & Transparency","score":100,"verdict":"pass","reasons":["Source repository is publicly reachable at the declared URL.","Cryptographically verified build provenance (signed, bound to base-buzz/paystage).","Clear OSI-approved license (MIT).","Actively maintained (last published 0 days ago).","Publishes a security disclosure policy (SECURITY.md)."],"codes":[{"code":"provenance.repo_verified","args":{}},{"code":"provenance.verified","args":{"repo":"base-buzz/paystage"}},{"code":"license.osi","args":{"spdx":"MIT"}},{"code":"maintenance.recent","args":{"age_days":"0"}},{"code":"disclosure.present","args":{}}]},{"name":"Schema Quality & AI Usability","score":60,"verdict":"fail","reasons":["AI-judged instruction clarity (good).","Context-footprint check failed: tool/resource definitions use about 1656 tokens (~165/item across 10 items; 10 tools + 0 resources), over budget; trim descriptions and params.","Usage-examples check failed: none of the tools include examples."],"codes":[{"code":"schema.ai_quality","args":{"band":"good"}},{"code":"schema.footprint_heavy","args":{"avg":"165","items":"10","tools":"10","tokens":"1656","resources":"0"}},{"code":"schema.examples_absent","args":{}}]},{"name":"Stability & Change Management","score":10,"verdict":"partial","reasons":["Stability observed for 3 of 30 days with no destabilising changes; credit accrues until the full window elapses."],"codes":[{"code":"stability.building_history","args":{"days":"3"}}]},{"name":"Tool Coverage","score":71,"verdict":"partial","reasons":["100% of tools have a non-trivial description (not blank, and not just the tool's name).","13% of tool parameters carry a description."],"codes":[{"code":"toolquality.descriptions","args":{"pct":"100"}},{"code":"toolquality.param_docs","args":{"pct":"13"}}]},{"name":"Tool Safety","score":100,"verdict":"pass","reasons":["No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.","We read all 10 captured tool definition(s), and no name or description among them implies an irreversible operation.","An AI judge read all 10 captured unit(s) of tool text and found none that tries to manipulate the model reading it."],"codes":[{"code":"toolsafety.injection_clean","args":{}},{"code":"toolsafety.destructive_none","args":{"tools":"10"}},{"code":"toolsafety.manipulation_clean","args":{"units":"10","judged":"10"}}]},{"name":"Capabilities","score":100,"verdict":"pass","reasons":["Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28."],"codes":[{"code":"protocol.supported","args":{"latest":"2026-07-28","version":"2025-11-25"}}]}],"inconclusive":[],"malware":[],"components":[{"slug":"api","type":"remote","identifier":"https://api.paystage.xyz/mcp","withdrawn":false,"score":63,"current":false,"url":"https://verifymcp.io/servers/base-buzz-x402-payment-safety/api","markdownUrl":"https://verifymcp.io/servers/base-buzz-x402-payment-safety/api.md"},{"slug":"paystage-mcp","type":"npm","identifier":"@paystage/mcp","withdrawn":false,"score":78,"current":true,"url":"https://verifymcp.io/servers/base-buzz-x402-payment-safety/paystage-mcp","markdownUrl":"https://verifymcp.io/servers/base-buzz-x402-payment-safety/paystage-mcp.md"}],"facts":[{"label":"Registry","value":"npm"},{"label":"Package","value":"@paystage/mcp"},{"label":"Version","value":"0.8.17"},{"label":"Transport","value":"stdio"}],"install":{"available":true,"bundleSha256":null},"tools":[{"name":"evaluate_mcp_payment","title":null,"description":"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. 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. 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.","inputs":[{"name":"agent_id","type":"string","required":false,"description":"Which agent is asking. Required to reach per-agent budgets in policy.agents."},{"name":"payment_identifier","type":"string","required":false,"description":"The x402 payment-identifier for this challenge, if the seller or client supplies one. Passing the same value on a retry turns the second verdict into `review` instead of a second `pay`, because a ret…"},{"name":"payment_required","type":null,"required":true,"description":null},{"name":"policy","type":null,"required":false,"description":null},{"name":"policy_path","type":"string","required":false,"description":null}],"outputs":[],"hasOutputSchema":false,"hasExamples":false,"tokenEstimate":270},{"name":"list_outstanding_auths","title":null,"description":"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.","inputs":[{"name":"eip3009_nonces","type":"array","required":false,"description":null},{"name":"network","type":"string","required":false,"description":null},{"name":"policy","type":null,"required":false,"description":null},{"name":"policy_path","type":"string","required":false,"description":null},{"name":"rpc_url","type":"string","required":false,"description":null},{"name":"spenders","type":"array","required":false,"description":null},{"name":"tokens","type":"array","required":false,"description":null},{"name":"wallet","type":"string","required":true,"description":null}],"outputs":[],"hasOutputSchema":false,"hasExamples":false,"tokenEstimate":181},{"name":"evaluate_outstanding_auths","title":null,"description":"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.","inputs":[{"name":"eip3009_nonces","type":"array","required":false,"description":null},{"name":"network","type":"string","required":false,"description":null},{"name":"policy","type":null,"required":false,"description":null},{"name":"policy_path","type":"string","required":false,"description":null},{"name":"rpc_url","type":"string","required":false,"description":null},{"name":"spenders","type":"array","required":false,"description":null},{"name":"tokens","type":"array","required":false,"description":null},{"name":"wallet","type":"string","required":true,"description":null}],"outputs":[],"hasOutputSchema":false,"hasExamples":false,"tokenEstimate":186},{"name":"evaluate_hip3_trade","title":null,"description":"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.","inputs":[{"name":"policy","type":null,"required":false,"description":null},{"name":"policy_path","type":"string","required":false,"description":null},{"name":"proposal","type":"object","required":true,"description":null},{"name":"snapshot","type":null,"required":false,"description":null}],"outputs":[],"hasOutputSchema":false,"hasExamples":false,"tokenEstimate":149},{"name":"evaluate_velocity","title":null,"description":"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.","inputs":[{"name":"history","type":"array","required":false,"description":null},{"name":"now_ms","type":"integer","required":false,"description":null},{"name":"policy","type":null,"required":false,"description":null},{"name":"policy_path","type":"string","required":false,"description":null},{"name":"proposed","type":"object","required":true,"description":null}],"outputs":[],"hasOutputSchema":false,"hasExamples":false,"tokenEstimate":155},{"name":"verify_receipt","title":null,"description":"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. 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.","inputs":[{"name":"key_url","type":"string","required":false,"description":"Override the published key location"},{"name":"receipt","type":null,"required":true,"description":"The receipt object as issued"}],"outputs":[],"hasOutputSchema":false,"hasExamples":false,"tokenEstimate":161},{"name":"decode_payment_required","title":null,"description":"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.","inputs":[{"name":"header","type":"string","required":true,"description":"The raw base64 value of the payment-required header"}],"outputs":[],"hasOutputSchema":false,"hasExamples":false,"tokenEstimate":140},{"name":"validate_policy","title":null,"description":"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.","inputs":[{"name":"policy","type":null,"required":true,"description":null}],"outputs":[],"hasOutputSchema":false,"hasExamples":false,"tokenEstimate":111},{"name":"request_testnet_funds","title":null,"description":"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.","inputs":[{"name":"address","type":"string","required":true,"description":null},{"name":"faucetUrl","type":"string","required":false,"description":null}],"outputs":[],"hasOutputSchema":false,"hasExamples":false,"tokenEstimate":162},{"name":"evaluate_batch","title":null,"description":"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.","inputs":[{"name":"payments","type":"array","required":true,"description":null},{"name":"policy","type":null,"required":true,"description":null}],"outputs":[],"hasOutputSchema":false,"hasExamples":false,"tokenEstimate":141}],"toolsTruncatedAtCapture":false,"diagnostics":{"capturedAt":"2026-11-21T00:07:27.000Z","track":"package","endpoint":null,"declaredUrl":null,"truncated":false,"tls":null,"dnssec":null,"auth":null,"httpsRedirect":null,"transports":[],"provenance":{"outcome":"verified","label":"Verified","reason":"verified","reasonLabel":"Verified","discovery":"attestation_endpoint","discoveryLabel":"Registry attestation endpoint","sourceRepo":null,"attestationSkipped":null,"attestationSkippedLabel":null},"installScripts":[],"installScriptsTotal":null,"vulnerabilities":[],"vulnerabilitiesTotal":null,"dependencies":{"nodes":9,"partial":false,"deprecated":null,"stale":null,"noRepo":null}},"mismatches":[],"changelog":{"trackingSince":"2026-11-18","recent":[{"id":"chg_01a1fb6d-edaa-7286-83bf-8bb811eaf363","kind":"check.reverified","summary":"Malware scan (unverified → pass)","materiality":"security","direction":"improvement","scoreDelta":null,"occurredOn":"2026-11-21","url":"https://verifymcp.io/servers/base-buzz-x402-payment-safety/paystage-mcp#chg-chg_01a1fb6d-edaa-7286-83bf-8bb811eaf363"},{"id":"chg_01a1fb6d-edab-7aac-9b14-cf7fb9011d83","kind":"score.total_changed","summary":"Trust score (62 → 78)","materiality":"functional","direction":"improvement","scoreDelta":16,"occurredOn":"2026-11-21","url":"https://verifymcp.io/servers/base-buzz-x402-payment-safety/paystage-mcp#chg-chg_01a1fb6d-edab-7aac-9b14-cf7fb9011d83"},{"id":"chg_01a1fa0b-93b0-759e-914a-ced639c43643","kind":"score.total_changed","summary":"Trust score (78 → 62)","materiality":"functional","direction":"regression","scoreDelta":-16,"occurredOn":"2026-11-20","url":"https://verifymcp.io/servers/base-buzz-x402-payment-safety/paystage-mcp#chg-chg_01a1fa0b-93b0-759e-914a-ced639c43643"},{"id":"chg_01a1fa0b-93a4-7192-b961-7d2c73d523cd","kind":"check.unverifiable","summary":"Malware scan (pass → unverified)","materiality":"security","direction":"regression","scoreDelta":null,"occurredOn":"2026-11-20","url":"https://verifymcp.io/servers/base-buzz-x402-payment-safety/paystage-mcp#chg-chg_01a1fa0b-93a4-7192-b961-7d2c73d523cd"},{"id":"chg_01a1fa0b-93ac-7981-90b4-9e59914e3408","kind":"check.measure","summary":"Schema quality (128 → 165)","materiality":"functional","direction":"regression","scoreDelta":null,"occurredOn":"2026-11-20","url":"https://verifymcp.io/servers/base-buzz-x402-payment-safety/paystage-mcp#chg-chg_01a1fa0b-93ac-7981-90b4-9e59914e3408"},{"id":"chg_01a1fa0b-93b0-705a-991c-9af860f8daa2","kind":"package.version_changed","summary":"Package version (0.8.15 → 0.8.17)","materiality":"functional","direction":"neutral","scoreDelta":null,"occurredOn":"2026-11-20","url":"https://verifymcp.io/servers/base-buzz-x402-payment-safety/paystage-mcp#chg-chg_01a1fa0b-93b0-705a-991c-9af860f8daa2"},{"id":"chg_01a1f643-d38d-7198-b769-72170006e2ad","kind":"check.reverified","summary":"Stability (unverified → 0.07)","materiality":"functional","direction":"improvement","scoreDelta":null,"occurredOn":"2026-11-20","url":"https://verifymcp.io/servers/base-buzz-x402-payment-safety/paystage-mcp#chg-chg_01a1f643-d38d-7198-b769-72170006e2ad"},{"id":"chg_01a1f643-d38e-7ba3-954b-d525720618a6","kind":"score.total_changed","summary":"Trust score (77 → 78)","materiality":"functional","direction":"improvement","scoreDelta":1,"occurredOn":"2026-11-20","url":"https://verifymcp.io/servers/base-buzz-x402-payment-safety/paystage-mcp#chg-chg_01a1f643-d38e-7ba3-954b-d525720618a6"},{"id":"chg_01a1f11f-1763-7c5e-8883-66ca8fe78a80","kind":"check.reverified","summary":"Malware scan (unverified → pass)","materiality":"security","direction":"improvement","scoreDelta":null,"occurredOn":"2026-11-19","url":"https://verifymcp.io/servers/base-buzz-x402-payment-safety/paystage-mcp#chg-chg_01a1f11f-1763-7c5e-8883-66ca8fe78a80"},{"id":"chg_01a1f11f-1764-74ff-a092-5f281ce0aba9","kind":"score.total_changed","summary":"Trust score (62 → 77)","materiality":"functional","direction":"improvement","scoreDelta":15,"occurredOn":"2026-11-19","url":"https://verifymcp.io/servers/base-buzz-x402-payment-safety/paystage-mcp#chg-chg_01a1f11f-1764-74ff-a092-5f281ce0aba9"},{"id":"chg_01a1f02c-3067-7099-8763-b0f9f8ea6421","kind":"score.first_scored","summary":"First indexed and scored","materiality":"functional","direction":"neutral","scoreDelta":null,"occurredOn":"2026-11-18","url":"https://verifymcp.io/servers/base-buzz-x402-payment-safety/paystage-mcp#chg-chg_01a1f02c-3067-7099-8763-b0f9f8ea6421"},{"id":"chg_01a1ee1a-8640-7aad-abd5-7521d8f74466","kind":"score.first_scored","summary":"First indexed and scored","materiality":"functional","direction":"neutral","scoreDelta":null,"occurredOn":"2026-11-18","url":"https://verifymcp.io/servers/base-buzz-x402-payment-safety/paystage-mcp#chg-chg_01a1ee1a-8640-7aad-abd5-7521d8f74466"}],"truncated":false,"feedUrl":"https://verifymcp.io/servers/base-buzz-x402-payment-safety/paystage-mcp/changelog.json"},"links":{"html":"https://verifymcp.io/servers/base-buzz-x402-payment-safety/paystage-mcp","markdown":"https://verifymcp.io/servers/base-buzz-x402-payment-safety/paystage-mcp.md","changelogJson":"https://verifymcp.io/servers/base-buzz-x402-payment-safety/paystage-mcp/changelog.json","changelogRss":"https://verifymcp.io/servers/base-buzz-x402-payment-safety/paystage-mcp.xml","external":[{"label":"npm package","href":"https://www.npmjs.com/package/@paystage/mcp"},{"label":"Socket report","href":"https://socket.dev/npm/package/@paystage/mcp"},{"label":"Repository","href":"https://github.com/base-buzz/paystage"},{"label":"Website","href":"https://paystage.xyz/"}]}}