Skip to content

MoneyTools Agent Guide MCP server

Which MCP servers are MoneyTools Agent Guide's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.

read 2026-11-03

← Back to MoneyTools Agent Guide

Whose server it is
  • Registry namedev.moneytools/pay-precheckverified in the MCP registry

The registry name sits under moneytools.dev. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

When we asked itchecked 2026-11-03
  • Stateanswerschecked 2026-11-03
  • Tools6
  • Server calls itselfx402-pay-precheck
  • Server version2.5.0
  • Protocol version2025-06-18

On 2026-11-03 the server answered initialize and tools/list without a sign-in. First answer in 60 ms.

Should an agent connect itNot proven either way yet
  • Its tools do every use case we checked: pre-check a third-party x402 endpoint before paying; verify that a USDC payment settled on-chain; convert a public web page to markdown.
  • Checked on 1 of the 7 days it takes to judge reliability.

Once connected

  • For "pre-check a third-party x402 endpoint before paying", the likely first call is x402_precheck.
  • For "verify that a USDC payment settled on-chain", the likely first call is x402_verify_settlement.
  • For "convert a public web page to markdown", the likely first call is web_read_markdown.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

Measured dailydaily checks: 1, the first on 2026-11-03
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 1 so far
  • What an agent can do with it3 of 3 use cases
  • Answeredmeasuring1 of the 7 daily checks it takes to print a share
  • Median first answer107 ms
  • Space in an agent's context≈ 1,607 tokensthe definitions of all its tools (6), which an agent carries on every turn
  • Tool definitionsA · 100 of 100
  • Typed results6 of 6 toolsdeclared outputSchema: results come typed, read once
  • Every tool passes all six checks.

What an agent can do with it

  • can do · pre-check a third-party x402 endpoint before paying
  • can do · verify that a USDC payment settled on-chain
  • can do · convert a public web page to markdown

Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?

Worth a look

None of the five warning signs in these definitions.

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

Tools it offers6 tools · read 2026-11-03
  • x402_recommend

    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…

  • x402_precheck

    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…

  • x402_verify_settlement

    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…

  • solana_mint_check

    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…

  • web_read_markdown

    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>…

  • email_check

    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…

How to connect

Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:

{
  "mcpServers": {
    "pay-precheck": {
      "type": "http",
      "url": "https://mcp.moneytools.dev/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http moneytools https://mcp.moneytools.dev/mcp

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://mcp.moneytools.dev/mcp as a custom connector in the settings.

OpenAPI spec

4 paths, read 2026-11-03. Open the spec ↗

Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.