Lumière PayCheck MCP server
io.github.Book0fEli/paycheckBook0fElistreamable-httpv1.10.0Scanned
Check x402 endpoints before your AI agent pays: grades, payment checks, refunds, receipts.
10 tools: 1 do something that can't be undone, 1 change things and 8 only read.
- Reads private data · 0
- Reads text others write · 4
- Can send data out · 5
- 1 finding
Tools listed without sign-in. Remote posture
With Anlyon
1 tool here does something that can't be undone. Govern it.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the Lumière PayCheck MCP server can do
The Lumière PayCheck MCP server is published by the GitHub account Book0fEli. It has 10 tools. It can do things that cannot be undone, such as sending, paying or publishing (check_payment) and create or change data (1 tool: report_outcome), but cannot delete data. 8 tools only read.
4 tools bring in text other people can write (check_endpoint, report_outcome, paid_test_receipts and 1 more); 5 tools can send data out of your system (check_endpoint, check_payment, report_outcome and 2 more).
The fixed checks matched 1 finding (annotation-conflict). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in, and its tools changed 3 times since Anlyon Radar first saw them.
Last scanned Nov 11, 2026, version 1.10.0.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
10 tools
Can't be undone 1Claude Code: ask
check_paymentDecide whether a specific x402 payment should go through: returns allow true/false with reasons.Can send data out1 finding
Why it is in this group
- The name "check_payment" says "payment": a word that usually means money moves, which cannot be taken back.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Findings
- Warn
The server marks "check_payment" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "check_payment" says "payment": a word that usually means money moves, which cannot be taken back.
Description, as the server wrote it Decide whether a specific x402 payment should go through: returns allow true/false with reasons. Checks the endpoint's trust verdict, that the amount is within your cap and not above the monitored price, and that the payTo wallet matches the one we've observed (catches swapped or hijacked wallets). Optionally (minOrganicShare) it also requires that enough of the seller's volume comes from independent buyers. Intended for right before a payment, with the amount, payTo, and network from the endpoint's 402 quote; allow is true only when every rule passes. Use check_endpoint instead if you only want an endpoint's grade without a quote in hand. Read-only and free; it doesn't make or block the payment itself. When allow is false, the reasons list explains why. pauseDuringRetest: true also holds payments while a failed paid test awaits its re-test. API docs: https://github.com/Book0fEli/lumiere-paycheck/blob/main/docs/api.md
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- title: Check an x402 payment before paying
Changes things 1Claude Code: ask
report_outcomeAfter paying an x402 endpoint, report whether you got what you paid for.Reads text others writeCan send data outNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it After paying an x402 endpoint, report whether you got what you paid for. Free, optional, and open to every agent: send the receipt from a Lumière PayCheck allow decision (paid plans), or the endpoint url plus the payment's transaction hash (anyone; we verify the payment on-chain, Base or Solana, within 24 hours). Answer the short questions in answers: gotResponse, matchedListing (yes/partly/no), charged (as_quoted/more/twice), dataUsable (yes/unsure/no), wouldPayAgain. Reports never change a grade by themselves: confirmations from independent buyers move the endpoint up our paid-test queue, and serious problems (nothing came back, charged more or twice) trigger a re-test; only our own paid test changes the grade. One report per payment; the seller's own wallet can't report on itself.
Annotations the server declares
- title: Report how a paid x402 call went
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
Only reads 8Show 8 read-only tools
catalog_statsGet an overview of the whole monitored x402 catalog: how many endpoints are monitored, how many fall into each verdict (proceed, caution, avoid, free, insufficient_data), and when …No findings
Why it is in this group
- The description's first verb is "get": a word for reading.
Description, as the server wrote it Get an overview of the whole monitored x402 catalog: how many endpoints are monitored, how many fall into each verdict (proceed, caution, avoid, free, insufficient_data), and when scores were last computed. Use it for context or reporting, for example to tell a user how much of the x402 ecosystem passes checks. Endpoints from a seller listing thousands of near-identical endpoints are counted once as bulk_listing until each has its own grade. It says nothing about any single endpoint: use check_endpoint for one endpoint, top_endpoints for a ranked list, or check_payment before paying. Read-only, free, no parameters.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- title: x402 catalog statistics
check_endpointGet the trust verdict for one x402 endpoint: score (0-100), grade (A-F), and verdict (proceed, caution, avoid, free, or insufficient_data), plus uptime, delivery-test status, payou…Reads text others writeCan send data outNo findings
Why it is in this group
- The description's first verb is "get": a word for reading.
What it can reach
- untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Claude Code: ask, because it is tagged outbound.
Description, as the server wrote it Get the trust verdict for one x402 endpoint: score (0-100), grade (A-F), and verdict (proceed, caution, avoid, free, or insufficient_data), plus uptime, delivery-test status, payout-wallet incidents, and how many independent buyers stand behind the seller's buyer wallets (we count customers, not wallets). Use it when you're deciding whether an endpoint is trustworthy at all, before you have a price quote. When you already have the 402 quote (amount and payTo) and are about to pay, use check_payment instead: it runs this same check and also verifies the price and wallet. To discover good endpoints rather than check a known one, use top_endpoints. Read-only and free; reflects monitoring every 30 minutes and real test payments, so a brand-new endpoint may return insufficient_data. Endpoints not in the catalog return monitored: false and are checked automatically: if one answers a valid x402 payment quote it joins the catalog within about 10 minutes (see intake). A retest field appears while a failed paid test awaits its re-test (the grade changes only if that fails too). API docs: https://github.com/Book0fEli/lumiere-paycheck/blob/main/docs/api.md
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- title: Check an x402 endpoint
get_full_reportGet instructions for buying the detailed paid report on one x402 endpoint (score breakdown, current price quote, wallet and price history, test-payment results).Reads text others writeCan send data outNo findings
Why it is in this group
- The name "get_full_report" says "get": a word for reading.
What it can reach
- untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Claude Code: ask, because it is tagged outbound.
Description, as the server wrote it Get instructions for buying the detailed paid report on one x402 endpoint (score breakdown, current price quote, wallet and price history, test-payment results). Returns the report URL, price, and network; it doesn't buy the report itself. The report is an x402 endpoint that your agent pays with any x402 client. Use it only when the free check_endpoint result isn't enough and the user wants the full history. The response also lists the other paid x402 checks (wallet risk, batch grades, watch alerts), paid the same way. Endpoints we don't monitor return 404 on the report URL and are never charged. API docs: https://github.com/Book0fEli/lumiere-paycheck/blob/main/docs/api.md
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- title: How to get a full trust report
list_sellersList the sellers behind the monitored x402 endpoints, grouped by domain, with each seller's endpoint count, verdict mix (proceed, caution, avoid, free, insufficient_data, bulk_list…No findings
Why it is in this group
- The name "list_sellers" says "list": a word for reading.
Description, as the server wrote it List the sellers behind the monitored x402 endpoints, grouped by domain, with each seller's endpoint count, verdict mix (proceed, caution, avoid, free, insufficient_data, bulk_listing), passing and paid-tested counts, and best grade. Use it to find which providers have trustworthy endpoints, search a provider by domain, or see who has endpoints to avoid. Open one seller's endpoints with seller_endpoints; for a single endpoint use check_endpoint. Read-only and free; the same data as lumierepaycheck.org/sellers, refreshed every few minutes.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- title: List x402 sellers by verdict
paid_test_receiptsGet the signed receipts for our real test payments to one x402 endpoint: the exact payment terms we paid and the response we got (as SHA-256 hashes), amount quoted and paid, payout…Reads text others writeCan send data outNo findings
Why it is in this group
- The description's first verb is "get": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "get" and "http": it reads web pages, which anyone can write.
- untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Claude Code: ask, because it is tagged outbound.
Description, as the server wrote it Get the signed receipts for our real test payments to one x402 endpoint: the exact payment terms we paid and the response we got (as SHA-256 hashes), amount quoted and paid, payout wallet, HTTP status, result and time, signed with our published Ed25519 key. Use it when a user or agent wants evidence behind a grade instead of the grade alone; check_endpoint gives the grade itself. The tester wallet and transaction appear only after that test wallet is retired (until then a hash commits to them). Read-only and free; receipts exist for tests since Nov 7, 2026.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- title: Signed paid-test receipts
reliability_reportGet the live x402 reliability numbers from our own paid tests over the last 30 days: how many endpoints delivered once paid, how often payments didn't go through, how many bad call…No findings
Why it is in this group
- The description's first verb is "get": a word for reading.
Description, as the server wrote it Get the live x402 reliability numbers from our own paid tests over the last 30 days: how many endpoints delivered once paid, how often payments didn't go through, how many bad calls still charged the buyer and how many were refunded, why paid calls fail, what calls cost, and the sellers that refund failed calls. Includes the same numbers from about 30 days earlier when available. Use it to answer questions about x402 reliability as a whole or which sellers refund; for one endpoint use check_endpoint, for one seller seller_endpoints. Read-only and free; recomputed every 6 hours. The same data is at lumierepaycheck.org/reliability.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- title: x402 reliability report
seller_endpointsList one seller's monitored x402 endpoints with each one's grade, score, verdict, 7-day uptime, median response time, whether a real test payment was delivered, and how many checks…No findings
Why it is in this group
- The description's first verb is "list": a word for reading.
Description, as the server wrote it List one seller's monitored x402 endpoints with each one's grade, score, verdict, 7-day uptime, median response time, whether a real test payment was delivered, and how many checks it's based on, plus the seller's counts per verdict and its refund record (how many of our failed paid calls it refunded in the last 30 days). Use it after list_sellers to pick the best endpoint from a provider, or to see which of a seller's endpoints to avoid. For the full reasons behind one endpoint's grade use check_endpoint. Read-only and free; 50 endpoints per page at most.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- title: One seller's x402 endpoints
top_endpointsList the x402 endpoints that are currently safest to pay (verdict proceed or caution, no payout-wallet incidents), best first, with score, grade, verdict, and whether a real test p…No findings
Why it is in this group
- The description's first verb is "list": a word for reading.
Description, as the server wrote it List the x402 endpoints that are currently safest to pay (verdict proceed or caution, no payout-wallet incidents), best first, with score, grade, verdict, and whether a real test payment was delivered. Use it to discover reliable endpoints or pick between providers. To evaluate one specific endpoint use check_endpoint; to approve a payment use check_payment. Read-only and free; rankings update as monitoring runs (every 30 minutes).
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- title: Most trustworthy x402 endpoints
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write4
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out5
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 18:57 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 2
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- HighThe whole server
The endpoint served tools/list without credentials, and the list has 2 tools that change things (1 irreversible, 1 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://lumierepaycheck.org/mcp?plans=1: tools/list returned 10 tools to an anonymous client, including check_payment (irreversible), report_outcome (write)
Findings
Matches of fixed checks, with the text they matched.
- Warncheck_payment
The server marks "check_payment" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "check_payment" says "payment": a word that usually means money moves, which cannot be taken back.
History
Changes to its tool definitions and to its remote endpoint, newest first.
Tools1 added, 2 changed.+1 added~2 changedView diff
- Added:reliability_reportOnly reads
- Changed:check_endpointOnly readsdescription
- Changed:seller_endpointsOnly readsdescription
Tools2 changed.~2 changedView diff
- Changed:check_endpointOnly readsdescription
- Changed:check_paymentCan't be undonedescriptioninputSchema
Tools3 added, 2 changed.+3 added~2 changedView diff
- Added:list_sellersOnly reads
- Added:paid_test_receiptsOnly reads
- Added:seller_endpointsOnly reads
- Changed:catalog_statsOnly readsdescription
- Changed:check_paymentCan't be undoneinputSchema
Install
Pinned to version 1.10.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http paycheck https://lumierepaycheck.org/mcp?plans=1claude mcp add --transport http paycheck https://lumierepaycheck.org/mcp?plans=1Run in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__paycheck__top_endpoints",
"mcp__paycheck__catalog_stats",
"mcp__paycheck__list_sellers",
"mcp__paycheck__seller_endpoints",
"mcp__paycheck__reliability_report"
],
"ask": [
"mcp__paycheck__check_endpoint",
"mcp__paycheck__check_payment",
"mcp__paycheck__report_outcome",
"mcp__paycheck__paid_test_receipts",
"mcp__paycheck__get_full_report"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as paycheck. Review it before you use it.
Capability tags behind 5 rules
- mcp__paycheck__check_endpoint untrusted-input, outbound
- mcp__paycheck__check_payment outbound
- mcp__paycheck__report_outcome untrusted-input, outbound
- mcp__paycheck__paid_test_receipts untrusted-input, outbound
- mcp__paycheck__get_full_report untrusted-input, outbound
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/io.github.Book0fEli/paycheck/verify?hash=99d4e9a875157dc0a6e3a8697121768ddb50a7f44d9843487164e98bbee786be" | jq -e '.changed == false'Pinned hash 99d4e9a87515, from Nov 11, 2026, 01:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.Book0fEli/paycheck/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.Book0fEli/paycheck)Source: MCP Registry · repository. Synced Nov 11, 2026, 01:17 UTC.
Lumière PayCheck MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Lumière PayCheck MCP server safe?
- No scan can promise that. What its definitions show: 10 tools, 2 of which can change, send or delete something, and 1 finding from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the Lumière PayCheck MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Lumière PayCheck MCP server do things that cannot be undone?
- Yes. 1 tool can send, pay, publish or merge: check_payment.
What tools does the Lumière PayCheck MCP server have?
- 10 tools: 1 irreversible, 1 write, 8 read. check_payment, report_outcome, check_endpoint, top_endpoints, catalog_stats, list_sellers, seller_endpoints, reliability_report and 2 more.
Does the Lumière PayCheck MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Lumière PayCheck MCP server send data to outside services?
- 5 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): check_endpoint, check_payment, report_outcome, paid_test_receipts and get_full_report.
Has the Lumière PayCheck MCP server changed its tools?
- Yes, 3 times since Anlyon Radar started tracking it, most recently on Nov 11, 2026. Every change is on this page and in its Atom feed.