{
  "markdown": "[![Glama MCP server score](https://glama.ai/mcp/servers/sF1nX/x402station-mcp/badges/score.svg)](https://glama.ai/mcp/servers/@sF1nX/x402station-mcp)\n\n# x402station-mcp\n\n<!-- mcp-name: io.github.sF1nX/x402station -->\n\nMCP adapter for **[x402station.io](https://x402station.io)**, the **independent risk-signal layer for x402 agentic commerce**. Exposes Preflight by x402station.io plus Forensics, Catalog Decoys, Alternatives, Credits, Watch, and Whats New. Any agent speaking the Model Context Protocol gets endpoint evidence before signing `PAYMENT-SIGNATURE` — **decoy, zombie, price-trap, never-paid, latency, signature/settlement checks** — before paying.\n\nx402station.io independently probes every endpoint listed on agentic.market every 10 minutes and merges probe history with CDP settlement data. Policy engines decide and enforce; x402station.io measures and reports. We do not route, take custody, or endorse.\n\n## Install\n\n```bash\n# Claude Code / Cursor / Windsurf / Continue — works anywhere with MCP\nnpm install -g x402station-mcp\n# or use npx in the config, no global install needed:\n```\n\n## Configure\n\nThe adapter charges real USDC per paid call through x402 itself. You need a wallet private key that holds Base mainnet USDC.\n\n### Claude Code\n\nAdd to `~/.claude/claude_desktop_config.json` (or wherever your MCP servers live):\n\n```json\n{\n  \"mcpServers\": {\n    \"x402station\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"x402station-mcp\"],\n      \"env\": {\n        \"AGENT_PRIVATE_KEY\": \"0xYOUR_PRIVATE_KEY_HERE\"\n      }\n    }\n  }\n}\n```\n\n### Cursor / Windsurf / Continue\n\nSame shape — every MCP host understands `command` / `args` / `env`. See your tool's MCP docs.\n\n### Environment\n\n| Variable | Required | Default | Purpose |\n|---|---|---|---|\n| `AGENT_PRIVATE_KEY` | **yes** for any paid tool call | — | 0x-prefixed 64-hex-char private key. Account must hold Base mainnet USDC. |\n| `X402STATION_BASE_URL` | no | `https://x402station.io` | Override for dev / testing. |\n\n## Tools\n\n### `preflight(url)` — $0.001 USDC\n\nAsk whether it's safe to pay this x402 URL. Returns:\n\n```json\n{\n  \"ok\": true,\n  \"warnings\": [],\n  \"metadata\": {\n    \"service\": \"...\",\n    \"price_usdc\": \"0.01\",\n    \"uptime_1h_pct\": 100,\n    \"avg_latency_ms\": 412\n  }\n}\n```\n\n`ok` is `true` only when no critical warning fires. Warnings include `unknown_endpoint`, `no_history`, `dead`, `zombie`, `decoy_price_extreme`, `never_paid_zombie`, `proxy_markup`, `wildcard_402`, `spa_fallback`, `suspicious_high_price`, `slow`, and `new_provider`.\n\n### `forensics(url)` — $0.001 USDC\n\nDeep 7-day report. Superset of preflight. Returns hourly uptime, latency p50/p90/p99, status-code distribution, concentration-group stats, decoy probability. Extra warnings: `dead_7d`, `mostly_dead`, `slow_p99`, `price_outlier_high`, `high_concentration`.\n\n### `catalog_decoys()` — $0.005 USDC\n\nFull blacklist. Returns every active endpoint currently flagged critical, plus per-reason counts. Pull periodically and cache locally — cheaper than preflighting every URL.\n\n## Typical agent flow\n\n```\nagent wants data from some_endpoint.com\n    │\n    ├─ preflight(\"https://some_endpoint.com/data\")  ← $0.001\n    │     ok: false, warnings: [\"decoy_price_extreme\"]\n    │\n    └─ skip; try the next candidate\n```\n\nFor bulk discovery, do `catalog_decoys()` once per day and treat the result as a set-difference against any URLs you're about to hit.\n\n## Composes with\n\nx402station checks whether the **endpoint** is safe (decoy / zombie / price-trap / never-paid) before an agent pays. It pairs naturally with a **payload** safety check — screening the payment metadata for PII before signing:\n\n```\nagent intent: pay some_endpoint.com\n    ├─ x402station    preflight(url)              ← is the ENDPOINT safe?\n    ├─ presidio-x402  screen_payment_metadata()   ← is the PAYLOAD safe?\n    └─ pay()\n```\n\n[`presidio-hardened-x402-mcp`](https://github.com/presidio-v/presidio-hardened-x402-mcp) screens payment metadata for PII before signing. The two servers are developed independently, on purpose — keeping the signals uncorrelated is the point. This is a composition pointer, not an endorsement; see their repo for the screening tool's behaviour and limits.\n\n## Links\n\n- Service: https://x402station.io\n- Manifest: https://x402station.io/.well-known/x402\n- OpenAPI: https://x402station.io/api/openapi.json\n- Dataset: https://huggingface.co/datasets/x402station/preflight-dataset-v0_1\n- GitHub: https://github.com/sF1nX/x402station-mcp\n- x402 spec: https://x402.org\n\n## Contact\n\n- General + commercial: <hello@x402station.io>\n- Bug reports: <https://github.com/sF1nX/x402station-mcp/issues>\n- Security disclosures (RFC 9116): <https://x402station.io/.well-known/security.txt>\n\n## License\n\nMIT\n",
  "bytes": 4739,
  "sha": "80e8b5a5316bfdc456b6150972128f9cb0c1c7091ded3018749339c14e01d647",
  "repo_slug": "sf1nx/x402station-mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_sf1nx_x402station_d26b0df1/readme"
}