cryptoapis-mcp-x402-pay: Instructions file for Claude Code

CLAUDE.md

cryptoapis-mcp-x402-pay CLAUDE.md is an instructions file for Claude Code from CryptoAPIs-io/cryptoapis-mcp-x402-pay. It costs 1,782 tokens per session, scanned A, original, MIT.

Project instructions for an MCP tool that fetches web resources and pays x402-protected requests. The tool authorizes payment, signs it locally with a wallet key, and retries the request.

In plain words
What is it for?
Use it to make HTTP requests that may require x402 payment, with limits and network choices supplied by the caller.
Why use it?
It lets an AI agent access paid HTTP resources while keeping the private signing key inside the local process.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md.

This is CryptoAPIs-io/cryptoapis-mcp-x402-pay's own configuration. It tells Claude Code how to work on cryptoapis-mcp-x402-pay itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything cryptoapis-mcp-x402-pay configures →

Reuse

Borrowing it

Nothing to install: this file belongs to CryptoAPIs-io/cryptoapis-mcp-x402-pay. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/CryptoAPIs-io/cryptoapis-mcp-x402-pay/master/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/CryptoAPIs-io/cryptoapis-mcp-x402-pay

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for cryptoapis-mcp-x402-pay CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/cryptoapis-io/cryptoapis-mcp-x402-pay/claude-md/github.svg)](https://agentmods.dev/instructions/cryptoapis-io/cryptoapis-mcp-x402-pay/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/cryptoapis-io/cryptoapis-mcp-x402-pay/claude-md"><img src="https://agentmods.dev/badge/instructions/cryptoapis-io/cryptoapis-mcp-x402-pay/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for cryptoapis-mcp-x402-pay CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/cryptoapis-io/cryptoapis-mcp-x402-pay/claude-md"><img src="https://agentmods.dev/badge/instructions/cryptoapis-io/cryptoapis-mcp-x402-pay/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,782 This file is loaded in full into every session.
When invoked 1,782 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.01782 $0.01782
Opus 5.5 $0.00713 $0.00713
Sonnet 5.5 $0.00356 $0.00356
Haiku 4.5 $0.00178 $0.00178

Measured 1mo ago against content hash 293cbb1e7bde, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

cryptoapis-mcp-x402-pay CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — @cryptoapis-io/mcp-x402-pay

MCP server with three tools. x402_pay: fetch an HTTP resource and, on a 402 Payment Required, auto-pay it with x402 (authorize → sign locally → retry) and return the paid response. The agentic buyer surface — an AI agent calls x402_pay(url, apiKey, walletId, privateKey) and paywalled endpoints just work. Sibling of mcp-signer (which it depends on for local signing) and the buyer SDK (cryptoapis-x402-buyer-sdk, whose orchestration this mirrors inside the monorepo).

Non-custodial + local-only

Like mcp-signer: stdio transport only, no HTTP server, no startup api-key. The buyer's private key is a per-call tool parameter, signs LOCALLY, and never leaves the process. apiKey (the X402_BUYER key) is used ONLY to call the buyer /authorize — never to sign.

Three tools, ONE payment core

  • x402_pay — pays an HTTP url (402 → X-PAYMENT header → retry).
  • x402_pay_tool — pays a TOOL on ANOTHER MCP server (challenge in the tool result → _meta["x402/payment"] → retry). Launches the upstream over stdio for the call.
  • x402_discover — browse the facilitator's catalogue (public, no key, no cost).

x402_pay and x402_pay_tool share src/tools/payCore.ts (select → authorize → sign → build PaymentPayload). Only the ENVELOPE differs: HTTP base64-encodes the payload into a header; MCP sends the same object RAW in _meta (it carries structured JSON natively). Put any change to the payment flow in payCore, never in one transport — the split exists precisely so a fix or a newly-enabled family cannot land on only one side. (The buyer SDK made the same split: payFlow.js.)

The flow (payCore.ts, used by both payers)

  1. The transport fetches/calls and detects a challenge (HTTP 402, or an isError tool result).
  2. Parse accepts, pick one (allowedNetworks-aware), enforce maxAmount cap.
  3. POST it to the buyer /authorize (apiKey + walletId) → { authorized, scheme, signingPayload }.
  4. Sign by the artifact scheme, calling the matching @cryptoapis-io/mcp-signer function with the per-family key (all six wired): eip712→evmSignTypedData, svm-transaction→svmPartialSign, tron-transaction→tronSignFromDetails, utxo-transaction→utxoSignFromDetails, kaspa-transaction→kaspaSignFromDetails, xrp-transaction→xrpSignFromDetails.
  5. Build the PaymentPayload — wire scheme is ALWAYS exact (the facilitator's parseEnvelope rejects anything else; the family comes from network). The /authorize scheme is the artifact type, NOT the wire scheme. Every family's parsePayload reads payload.transaction first, so the wrapper is uniform payload:{transaction: <value>} — but the VALUE differs per family: EVM {signature, authorization}; SVM base64; UTXO/XRP signed hex; Kaspa signed JSON; Tron the structured {txID, raw_data_hex, raw_data, signature[]} object (the facilitator rejects a bare hex — hence mcp-signer's tronSignFromDetails additively returns signedTransaction). Base64 → X-PAYMENT header, retry once, return {status, paid, body, settlement?}.

Read the full file on GitHub · 87 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 1mo ago Changed · +23 lines · +442 tokens per session 293cbb1e7bde
  2. 2mo ago First seen · 64 lines · 1,340 tokens per session scan A 1384e0880497

Subscribe to this mod's changes

cryptoapis-mcp-x402-pay CLAUDE.md is an instructions file published in the GitHub repository CryptoAPIs-io/cryptoapis-mcp-x402-pay (0 stars, last pushed 10d ago), licensed MIT. It adds 1,782 tokens to every session, about $0.0071 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

cryptoapis-mcp-x402-pay CLAUDE.md compared with instructions from other repositories

cryptoapis-mcp-x402-pay CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
cryptoapis-mcp-x402-pay CLAUDE.mdCryptoAPIs-io/cryptoapis-mcp-x402-payInstructions file010d agoMITA1,782Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode