Skip to main content
Glama
x402station-mcp

x402station-mcp

by sF1nX

x402station-mcp

MCP-адаптер для предполетного оракула x402station. Предоставляет любому агенту, использующему протокол Model Context Protocol, инструменты preflight, forensics и catalog_decoys, чтобы он мог проверять эндпоинты x402 на наличие приманок, «зомби-сервисов» и ценовых ловушек перед их оплатой.

x402station независимо проверяет каждый эндпоинт, указанный на agentic.market (более 20 тыс. эндпоинтов каждые 10 минут) — он видит то, что не могут увидеть мониторы на основе фасилитаторов, включая около 161 эндпоинта со стоимостью ≥ $1,000 USDC, которые функционируют как ханипоты для защиты от парсинга.

Установка

# Claude Code / Cursor / Windsurf / Continue — works anywhere with MCP
npm install -g x402station-mcp
# or use npx in the config, no global install needed:

Related MCP server: RMI MCP + x402 Gateway

Настройка

Адаптер взимает реальные USDC за каждый вызов (через сам x402 — наш оракул использует собственные инструменты). Вам понадобится приватный ключ кошелька, на котором есть Base Sepolia USDC (или Base mainnet, когда мы перейдем на него).

Claude Code

Добавьте в ~/.claude/claude_desktop_config.json (или туда, где находятся ваши MCP-серверы):

{
  "mcpServers": {
    "x402station": {
      "command": "npx",
      "args": ["-y", "x402station-mcp"],
      "env": {
        "AGENT_PRIVATE_KEY": "0xYOUR_PRIVATE_KEY_HERE"
      }
    }
  }
}

Cursor / Windsurf / Continue

Аналогично — каждый MCP-хост понимает command / args / env. См. документацию MCP вашего инструмента.

Окружение

Переменная

Обязательно

По умолчанию

Назначение

AGENT_PRIVATE_KEY

да для любого вызова инструмента

—

Приватный ключ из 64 шестнадцатеричных символов с префиксом 0x. На аккаунте должны быть Base Sepolia USDC.

X402STATION_BASE_URL

нет

https://x402station.io

Переопределение для разработки / тестирования.

Тестовые USDC для кошелька: faucet.circle.com (выберите Base Sepolia).

Инструменты

preflight(url) — $0.001 USDC

Запрос о том, безопасно ли оплачивать этот URL x402. Возвращает:

{
  "ok": true,
  "warnings": [],
  "metadata": {
    "service": "...",
    "price_usdc": "0.01",
    "uptime_1h_pct": 100,
    "avg_latency_ms": 412
  }
}

ok равно true только в том случае, если не сработало ни одно критическое предупреждение. Предупреждения: unknown_endpoint, no_history, dead, zombie, decoy_price_extreme, suspicious_high_price, slow, new_provider.

forensics(url) — $0.001 USDC

Глубокий 7-дневный отчет. Супермножество preflight. Возвращает почасовой аптайм, задержку p50/p90/p99, распределение кодов состояния, статистику групп концентрации, вероятность приманки. Дополнительные предупреждения: dead_7d, mostly_dead, slow_p99, price_outlier_high, high_concentration.

catalog_decoys() — $0.005 USDC

Полный черный список. Возвращает каждый активный эндпоинт, помеченный в данный момент как критический, плюс количество по каждой причине. Запрашивайте периодически и кэшируйте локально — это дешевле, чем делать preflight для каждого URL.

Типичный агентский поток

agent wants data from some_endpoint.com
    │
    ├─ preflight("https://some_endpoint.com/data")  ← $0.001
    │     ok: false, warnings: ["decoy_price_extreme"]
    │
    └─ skip; try the next candidate

Для массового обнаружения выполняйте catalog_decoys() раз в день и используйте результат как разность множеств для любых URL, к которым вы собираетесь обратиться.

Ссылки

Контакты

Лицензия

MIT

Available Tools

10 tools
alternativesRouting fallback — siblings to a flagged endpointA

Given a URL flagged by preflight (or a taskClass hint), returns up to 5 healthy sibling endpoints in the same provider/domain/category/price-band. Filters out 7-day-dead and 1-hour-erroring candidates; ranks by uptime + latency. Costs $0.005 USDC. Use this immediately after preflight returns ok=false — it answers 'where do I go instead?'. Pass {url} when you have a specific URL the agent was about to pay; pass {taskClass} (e.g. 'llm-completions', 'Inference') when discovering by service category; or both for a richer match.

Inputs: url, taskClass, limit.

buy_creditsBuy 1000 prepaid /api/v1/preflight calls ($0.50 = 50% off)A

Bulk-prepaid preflight bundle. Pay $0.50 USDC once for 1000 prepaid /api/v1/preflight calls. Effective rate $0.0005/call (50% off the per-call $0.001 tier). Returns { creditId, balance: 1000, expiresAt }. STORE THE creditId — it's the bearer token and is not retrievable later. Pass it via X-Credit-Id header on subsequent /api/v1/preflight calls; on exhaustion (balance=0) or expiry (90 days) the middleware falls through to per-call x402 automatically. Use this once you've decided to do high-volume preflight work.

Inputs: no named parameters.

catalog_decoysFull decoy / zombie blacklistA

Returns every active x402 endpoint currently flagged decoy_price_extreme / zombie / dead_7d / mostly_dead in one JSON payload, plus per-reason counts. Costs $0.005 USDC. Pull periodically (hourly/daily) and cache locally as a blacklist — cheaper than preflighting every URL.

Inputs: no named parameters.

credits_statusRead a credit's current balance + expiryA

Free, no payment required. Returns { creditId, balance, initialBalance, used, paidAmount, createdAt, expiresAt, expired, paymentTx, paymentNetwork }. UUID-only access — anyone holding the creditId can read state, same as decrement. 404 covers both 'malformed UUID' and 'no such credit' (same body so an attacker scraping random UUIDs can't tell them apart).

Inputs: creditId (required).

forensics7-day forensics reportA

Deep history for one x402 endpoint: hourly uptime over 7 days, latency p50/p90/p99, status-code distribution, concentration-group stats (how crowded this provider's namespace is), and a decoy probability score [0, 1]. Costs $0.001 USDC. Superset of preflight — if you're running forensics you don't need preflight too.

Inputs: url (required).

preflightPre-flight safety checkA

Ask x402station whether a given x402 URL is safe to pay. Returns {ok, warnings[], metadata}. Costs $0.001 USDC (auto-signed with AGENT_PRIVATE_KEY). Call this BEFORE any other paid x402 request to avoid decoys (price ≥ $1k), zombie services, and dead endpoints. ok:true only when no critical warning fires.

Inputs: url (required).

watch_statusCheck watch subscription status + recent alertsA

Returns the current state of a watch: active/expired, alerts remaining (out of 100 prepaid), last 10 alert deliveries with their delivery_status, and the last computed signal snapshot. Free — no payment required, secret-gated. The secret is the one returned by watch_subscribe.

Inputs: watchId (required), secret (required).

watch_subscribeSubscribe to webhook alerts on x402 endpoint state changesA

Pay $0.01 USDC for a 30-day watch + 100 prepaid alerts on one x402 endpoint. When subscribed signals fire or clear (e.g. endpoint goes zombie, price flips to decoy_price_extreme), x402station POSTs a JSON payload signed with HMAC-SHA256 to your webhookUrl. Returns watchId + secret — STORE THE SECRET, it's the HMAC seed for verifying delivery payloads and is not retrievable later. signals defaults to the critical preflight subset {dead, zombie, decoy_price_extreme}; pass other names to subscribe to non-critical signals too.

Inputs: url (required), webhookUrl (required), signals.

watch_unsubscribeUnsubscribe from a watch (deactivate)A

Deactivates the watch — no further alerts will be queued or delivered. The subscription is set is_active=false but the row + alert history is retained for audit. Free — no payment required, secret-gated. There is no refund for unused prepaid alerts.

Inputs: watchId (required), secret (required).

whats_newCatalog diff polling — added / removed endpoints since `since`A

Polling-friendly catalog diff. Body { since?, limit? } (default since=now-24h, limit=200, max 500). Returns added_endpoints[] (first_seen_at >= since AND is_active=true), removed_endpoints[] (flipped to is_active=false since), service-level counts, polls_in_window, and current active totals. Cheap ($0.001 USDC) so hourly polling stays under $1/month — perfect for aggregator agents that need a fresh delta without re-pulling the whole catalog. Internal ingest cron runs every 5 min, so polling more often than that returns identical data.

Inputs: since, limit.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4.4/5.0

    Scored across 10 tools

    Disambiguation5/5

    Each tool serves a distinct function: preflight checks, alternative endpoints, credit management, forensics, catalog blacklists, watch subscriptions, and catalog diffs. Descriptions are detailed, leaving no ambiguity about tool purposes.

    Naming Consistency5/5

    All tool names follow a consistent verb_noun pattern in snake_case (e.g., buy_credits, watch_subscribe, whats_new), making predictions and selection straightforward for an agent.

    Tool Count5/5

    With 10 tools, the server covers its domain of endpoint safety monitoring, credit management, and subscription alerts without being overly bloated or sparse.

    Completeness4/5

    The tool surface covers the main workflow: preflight checks, alternatives, credit buying, status, forensics, blacklisting, watching, and polling. A minor gap is the lack of a free endpoint status query for a single URL, but the paid preflight covers it.

    Maintenance

    ActivityInactive
    ResponsivenessMixed handling

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      F
      maintenance
      Archived and no longer maintained. Tools and prices shown here are out of date. Use the maintained server: glama.ai/mcp/servers/OceanAlt666/oceanalt-aml-mcp (GitHub: OceanAlt666/oceanalt-aml-mcp).
      164 npm
      MIT
    • A
      license
      Not graded
      quality
      B
      maintenance
      Exposes typed crypto-security tools — token risk scoring, wallet forensics, deployer reputation, sentiment, and report generation — to MCP-capable agents over streamable HTTP or stdio. Gates premium calls behind per-request x402 crypto micropayments, delegating verification and settlement to a self-hosted facilitator and failing closed when payment cannot be confirmed.
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables AI agents to access pay-per-call onchain and URL safety APIs over MCP, covering transaction explanations, token approval checks, address inspection, contract risk heuristics, URL safety, gas snapshots, ENS resolution, calldata decoding, and wallet portfolio data. Payments are handled per call in USDC on Base via x402, with no signup or API key required.
      1
      MIT
    • A
      license
      Not graded
      quality
      B
      maintenance
      Enables AI agents to run a free fail-closed preflight gate on x402 payment challenges and transactions before signing, plus five USDC-paid on-chain truth checks covering arbitrage profitability, token safety, swap routing, quote validation, and trade sizing. Each check returns a verdict with pinned-block evidence and a verifiable receipt.
      Apache 2.0