Cursor editor rules for developing the 402-mcp project, a server that lets AI agents discover, pay for, and use payment-protected APIs. They describe commands, code conventions, testing practices, and security requirements.

They guide Cursor through building, testing, and type-checking the project, writing testable tool handlers, tracking spending safely, validating payment data, and guarding outgoing requests.

They prevent an AI coding assistant from guessing how the project works or introducing changes that conflict with its payment and network-safety rules.

cursorrules — Cursor rule by forgesworn

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods

npx agentmods add rules/forgesworn/402-mcp/cursorrules

Clone the repo

git clone --depth 1 https://github.com/forgesworn/402-mcp

Made for: Cursor.

Per session 554 This file is loaded in full into every session.

When invoked 554 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

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.

Model	Per session	Once invoked
Fable 5	$0.00554	$0.00554
Opus 5	$0.00277	$0.00277
Sonnet 5	$0.00111	$0.00111
Haiku 4.5	$0.00055	$0.00055

Measured yesterday against content hash dbb2b97136d3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cursorrules 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 yesterday.

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.

.cursorrules · 37 lines

How it starts

The opening of the file, as written. The whole thing — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cursor Rules — 402-mcp

L402 + x402 client MCP server. AI agents discover, pay for, and consume any payment-gated API autonomously.

Commands

npm run build — compile TypeScript to build/
npm test — run all tests (vitest)
npm run typecheck — type-check without emitting

Conventions

British English — colour, initialise, behaviour, licence
ESM-only — "type": "module", target ES2022, module Node16
Tool pattern — each tool file exports a handle* function (testable with injected deps) and a register*Tool function (MCP wiring)
Tests live in tests/, not co-located with source. Each handler's handle* function is tested directly with mock deps using vi.fn()
Commit messages — type: description format (feat:, fix:, docs:, chore:, refactor:). No Co-Authored-By lines.

Key Patterns

Atomic spend tracking — always use spendTracker.tryRecord(sats, limit), never split wouldExceed() + record() (TOCTOU race)
Preimage validation — validate hex format before storing. Preimages are sent raw in Authorization: L402 {macaroon}:{preimage} headers
SSRF guard — all outbound HTTP goes through the SSRF guard. Money-mutating POSTs pass { retries: 0 } to disable retry
cashu-ts v2 — getDecodedToken() returns { mint, proofs, unit } at top level. There is NO .token array
nostr-tools NIP-44 — use getConversationKey(privkey, pubkey) then encrypt(plaintext, conversationKey). Do NOT use NIP-04

Structure

src/index.ts — entry point: config, wiring, transport setup
src/config.ts — environment variable parsing with validation
src/tools/ — one file per MCP tool (handler + registration)
src/wallet/ — payment implementations (NWC, Cashu, human-in-the-loop)
src/store/ — persistent JSON stores (credentials, Cashu tokens)
src/l402/ — L402 protocol utilities (parse, detect, cache, bolt11)
src/fetch/ — resilient fetch: SSRF guard, timeout, retry, transport selection
tests/ — mirrors src/ structure

Read the full file on GitHub · 37 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.

yesterday First seen · 37 lines · 554 tokens per session scan A dbb2b97136d3

Subscribe to this mod's changes

cursorrules is a cursor rule published in the GitHub repository forgesworn/402-mcp (0 stars, last pushed 10d ago), licensed MIT. It adds 554 tokens to every session, about $0.0028 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.

Backend and APIs Security Testing ai-agents bitcoin cashu ecash http-402 l402

cursorrules

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Cursor Rules — 402-mcp

Commands

Conventions

Key Patterns

Structure

What this file has done since we first saw it

Other cursor rules, from other repositories

e2e-script

agent-files

bun

3rd-library

pkg-or-internal

documentation-language