Borrowing it
Nothing to install: this file belongs to CryptoAPIs-io/cryptoapis-mcp-x402-accept. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/CryptoAPIs-io/cryptoapis-mcp-x402-accept/main/CLAUDE.mdgit clone --depth 1 https://github.com/CryptoAPIs-io/cryptoapis-mcp-x402-acceptWrote 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.
[](https://agentmods.dev/instructions/cryptoapis-io/cryptoapis-mcp-x402-accept/claude-md)<a href="https://agentmods.dev/instructions/cryptoapis-io/cryptoapis-mcp-x402-accept/claude-md"><img src="https://agentmods.dev/badge/instructions/cryptoapis-io/cryptoapis-mcp-x402-accept/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.
<a href="https://agentmods.dev/instructions/cryptoapis-io/cryptoapis-mcp-x402-accept/claude-md"><img src="https://agentmods.dev/badge/instructions/cryptoapis-io/cryptoapis-mcp-x402-accept/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.01027 | $0.01027 |
| Opus 5 | $0.00513 | $0.00513 |
| Sonnet 5 | $0.00205 | $0.00205 |
| Haiku 4.5 | $0.00103 | $0.00103 |
Grade A, and why
cryptoapis-mcp-x402-accept 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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — @cryptoapis-io/mcp-x402-accept
The merchant-side MCP paywall proxy. Fronts an MCP server the merchant already runs and charges
agents per tool call with x402, without touching that server's code. The mirror image of
mcp-x402-pay (which is the buyer side).
agent → mcp-x402-accept (MERCHANT's process) → merchant's MCP server
It is an MCP server to the agent and an MCP client to the upstream — the only package in this monorepo that is both.
Non-negotiable: self-hosted only
CryptoAPIs never runs this process, and we do not offer a hosted version — decided deliberately (BL-0162), not a default. Hosting it would mean holding merchants' upstream credentials, sitting in the cleartext path of their tool arguments and results, taking on a GDPR data-processor role, and owing uptime on their revenue. Self-hosting removes the question instead of answering it.
That decision is load-bearing on the CODE, and must survive future edits:
- Tool arguments and results are OPAQUE. The proxy reads only the tool name and
_meta["x402/payment"]. Never parse, log, buffer or cache args/results.upstream.callTooland the handlers inpaywall.tsforward verbatim — keep them that way. - Never log to stdout. On a stdio MCP server stdout is the protocol stream; a stray line corrupts it. Diagnostics go to stderr, and are counts only — never payloads.
Note the sibling mcp-x402-pay logs every tool call via McpLogger. This package deliberately does
not — it would defeat the opacity guarantee above.
Modules (src/)
config.ts— zod-validated JSON config +${VAR}env interpolation (so the file holds no secrets and stays commit-safe). Everything fails at boot, never on an agent's first paid call.upstream.ts— the outbound MCP client (stdioorstreamableHttp). Connect, list, forward. Nothing else belongs here.paywall.ts— wraps an upstream tool using the merchant SDK'spaymentTool. Reuses@cryptoapis-io/x402-merchant-sdk/mcprather than reimplementing the transport, so the template (the SDK'sexamples/mcp-paid-tool/) and this proxy share ONE x402 MCP implementation and a spec fix lands in both. Do not fork that logic in here.server.ts— mirrors upstream tools, registering each as paid or free; boots the stdio server.cli.ts—cryptoapis-mcp-x402-accept --config <path>.
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.
- 12d ago First seen · 80 lines · 1,027 tokens per session scan A 180836c8f91e
cryptoapis-mcp-x402-accept CLAUDE.md is an instructions file published in the GitHub repository CryptoAPIs-io/cryptoapis-mcp-x402-accept (0 stars, last pushed 1mo ago), licensed MIT. It adds 1,027 tokens to every session, about $0.0051 per session on Opus 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.
Other instructions, from other repositories
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).