x402 agent toolkit: service finder, payment safety, Solana & web tools
dev.workers.moneytools.x402-pay-precheck/pay-precheckx402-pay-precheck.moneytools.workers.devstreamable-httpv2.1.0Scanned
x402 tools: service finder, payment precheck/verify, Solana mint check, web-to-Markdown, email check
6 tools: 3 change things and 3 only read.
- Reads private data · 0
- Reads text others write · 6
- Can send data out · 2
- No findings
Anlyon alternative
3 of these tools change something. Run those as governed actions.
Declare what an action changes, and Anlyon puts it under a shared limit, binds every approval to the exact request, and grades the outcome. It works on any HTTPS API you can describe as an action.
Anlyon does not run, proxy or govern this MCP server. A tool your own code calls directly is not routed through Anlyon and is not governed by it.
Import an OpenAPI spec →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.
6 tools
Changes things 3Claude Code: ask
solana_mint_checkRule-based safety check of a Solana SPL / Token-2022 mint: mint & freeze authority, permanent delegate, transfer hook/fee, pausable, default-frozen, largest-holder concentration.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Rule-based safety check of a Solana SPL / Token-2022 mint: mint & freeze authority, permanent delegate, transfer hook/fee, pausable, default-frozen, largest-holder concentration. Returns riskScore 0-100 and verdict low|medium|high. Paid HTTP: /v1/sol-mint. Referral program: add ref=<your 0x Base wallet> to paid HTTP calls you route here and earn 20% of net revenue = amount received minus facilitator and gas fees (off-chain ledger, settled monthly in USDC on Base after manual review, min 1 USDC; earnings at GET /v1/referral/{address}).
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
x402_precheckBefore paying an x402 endpoint: fetch it, validate its HTTP 402 payment requirements (scheme, network, payTo, amount, asset) and screen payTo against the OFAC SDN crypto-address li…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.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
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 Before paying an x402 endpoint: fetch it, validate its HTTP 402 payment requirements (scheme, network, payTo, amount, asset) and screen payTo against the OFAC SDN crypto-address list. Returns verdict ok|warn|block|not_402. Referral program: add ref=<your 0x Base wallet> to paid HTTP calls you route here and earn 20% of net revenue = amount received minus facilitator and gas fees (off-chain ledger, settled monthly in USDC on Base after manual review, min 1 USDC; earnings at GET /v1/referral/{address}).
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
x402_verify_settlementVerify an on-chain USDC settlement: tx hash on network (base, base-sepolia, polygon, arbitrum, avalanche, bsc) paid amount to payTo.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Verify an on-chain USDC settlement: tx hash on network (base, base-sepolia, polygon, arbitrum, avalanche, bsc) paid amount to payTo. Returns verdict valid|invalid|pending|not_found. Referral program: add ref=<your 0x Base wallet> to paid HTTP calls you route here and earn 20% of net revenue = amount received minus facilitator and gas fees (off-chain ledger, settled monthly in USDC on Base after manual review, min 1 USDC; earnings at GET /v1/referral/{address}).
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
Only reads 3Show 3 read-only tools
email_checkValidate an email address without sending mail or SMTP probing: syntax, domain exists, MX / null-MX, SPF, DMARC, disposable domain (10k+ list), role account, free provider, typo su…Reads text others writeNo findings
Why it is in this group
- The description's first verb is "validate": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Validate an email address without sending mail or SMTP probing: syntax, domain exists, MX / null-MX, SPF, DMARC, disposable domain (10k+ list), role account, free provider, typo suggestion. Verdict valid|risky|invalid. Paid HTTP: /v1/email-check. Referral program: add ref=<your 0x Base wallet> to paid HTTP calls you route here and earn 20% of net revenue = amount received minus facilitator and gas fees (off-chain ledger, settled monthly in USDC on Base after manual review, min 1 USDC; earnings at GET /v1/referral/{address}).
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
web_read_markdownFetch a public web page and return clean Markdown (title, headings, links, lists, code) with a sha256 of the content.Reads text others writeCan send data outNo findings
Why it is in this group
- The name "web_read_markdown" says "read": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe name "web_read_markdown" says "read" and "web": it reads web pages, which anyone can write.
- untrusted-inputThe description's first sentence says "fetch" and "web": 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 Fetch a public web page and return clean Markdown (title, headings, links, lists, code) with a sha256 of the content. Respects robots.txt, public pages only, 1h cache. Paid HTTP: /v1/read. Referral program: add ref=<your 0x Base wallet> to paid HTTP calls you route here and earn 20% of net revenue = amount received minus facilitator and gas fees (off-chain ledger, settled monthly in USDC on Base after manual review, min 1 USDC; earnings at GET /v1/referral/{address}).
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
x402_recommendFind which x402 paid service to call for a task.Reads text others writeNo findings
Why it is in this group
- The description's first verb is "find": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Find which x402 paid service to call for a task. Returns endpoints ranked by relevance and live liveness (unpaid probe returned valid x402 terms, payTo OFAC-screened), latency and price; top 3 freshly pre-checked. Referral program: add ref=<your 0x Base wallet> to paid HTTP calls you route here and earn 20% of net revenue = amount received minus facilitator and gas fees (off-chain ledger, settled monthly in USDC on Base after manual review, min 1 USDC; earnings at GET /v1/referral/{address}).
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
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 write6
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out2
- 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.
Findings
Matches of fixed checks, with the text they matched.
No check matched anything in these tool definitions. That is not a safety guarantee.
History
Changes to its tool definitions and to its remote endpoint, newest first.
Tools3 added.+3 addedView diff
- Added:email_checkOnly reads
- Added:solana_mint_checkChanges things
- Added:web_read_markdownOnly reads
Install
Pinned to version 2.1.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http pay-precheck https://x402-pay-precheck.moneytools.workers.dev/mcpclaude mcp add --transport http pay-precheck https://x402-pay-precheck.moneytools.workers.dev/mcpRun 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__pay-precheck__x402_recommend",
"mcp__pay-precheck__email_check"
],
"ask": [
"mcp__pay-precheck__x402_precheck",
"mcp__pay-precheck__x402_verify_settlement",
"mcp__pay-precheck__solana_mint_check",
"mcp__pay-precheck__web_read_markdown"
],
"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 pay-precheck. Review it before you use it.
Capability tags behind 6 rules
- mcp__pay-precheck__x402_recommend untrusted-input
- mcp__pay-precheck__x402_precheck untrusted-input, outbound
- mcp__pay-precheck__x402_verify_settlement untrusted-input
- mcp__pay-precheck__solana_mint_check untrusted-input
- mcp__pay-precheck__web_read_markdown untrusted-input, outbound
- mcp__pay-precheck__email_check untrusted-input
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://anlyon.dev/api/v1/servers/dev.workers.moneytools.x402-pay-precheck/pay-precheck/verify?hash=3d89f1a60802da17dea5aca090aa0c6af4510cdf7efb730c12781a443c3df0ff" | jq -e '.changed == false'Pinned hash 3d89f1a60802, from Nov 3, 2026, 08:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://anlyon.dev/servers/dev.workers.moneytools.x402-pay-precheck/pay-precheck/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://anlyon.dev/servers/dev.workers.moneytools.x402-pay-precheck/pay-precheck)Source: MCP Registry. Synced Nov 3, 2026, 08:17 UTC.