{
  "markdown": "# @melis-ai/x402-tools-mcp\n\n[![npm version](https://img.shields.io/npm/v/@melis-ai/x402-tools-mcp.svg)](https://www.npmjs.com/package/@melis-ai/x402-tools-mcp)\n[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)\n[![MCP compatible](https://img.shields.io/badge/MCP-compatible-blue.svg)](https://modelcontextprotocol.io)\n[![x402](https://img.shields.io/badge/x402-protocol-7c3aed.svg)](https://x402.org)\n[![Catalogue](https://img.shields.io/badge/catalogue-agents.melis.ai-teal.svg)](https://agents.melis.ai)\n\nBoring infrastructure for agent builders. **22 pay-per-call utility tools** served as an MCP server — scrape, validate, embed, store, moderate, notify, convert, prevent loops. **No accounts, no API keys, no subscriptions.** Pay with USDC on Base via the [x402 protocol](https://x402.org).\n\n```bash\nnpx @melis-ai/x402-tools-mcp\n```\n\n→ Full catalogue with prices and live examples: **[agents.melis.ai](https://agents.melis.ai)**\n→ Canonical 5-step RAG pipeline: **[agents.melis.ai/pipelines/rag](https://agents.melis.ai/pipelines/rag)**\n→ 5-minute getting started: **[agents.melis.ai/docs/getting-started](https://agents.melis.ai/docs/getting-started)**\n\n---\n\n## Tool catalogue (22)\n\n| Tool | Price (USDC) | Description |\n|------|-------------|-------------|\n| `list_services` | free | Returns the full catalogue with prices and endpoint URLs |\n| `cacheserve` | $0.001 | Fetch a URL with server-side caching — avoids redundant origin hits |\n| `docconvert_text` | $0.001 | Format conversion: md↔html, json↔csv, html→txt, etc. |\n| `intentflow` | $0.001 | Context handoff relay for multi-agent delegation (async, returns retrieve_url) |\n| `memoryserve_write` | $0.001 | Store text + embedding in Qdrant + SQLite, namespaced per `agent_id` |\n| `memoryserve_query` | $0.001 | Recall most-similar memories by semantic query |\n| `memscrub` | $0.001 | Scan retrieved RAG content for indirect prompt injection (10 patterns) |\n| `notifyrelay_webhook` | $0.001 | POST a JSON payload to a URL with optional HMAC-SHA256 signing |\n| `schemagate` | $0.001 | Validate a JSON response against a JSON Schema, return a hint on failure |\n| `loopwall_hop` | $0.0005 | Validate one hop of a signed multi-agent chain (loop / budget enforcement) |\n| `loopwall_issue` | $0.001 | Issue a signed Job Envelope at chain start with budget + hop cap |\n| `imageguard` | $0.002 | NSFW image classification (multi-class moderation on roadmap) |\n| `notifyrelay_telegram` | $0.002 | Send a Telegram message to a known chat ID |\n| `promptguard` | $0.002 | Score untrusted input for prompt injection risk (0–100) |\n| `structextract` | $0.002 | Extract structured JSON from HTML — tables, links, emails, phones |\n| `xaudit` | $0.002 | Validate API response content with a cryptographically signed certificate |\n| `docconvert_pdf` | $0.005 | Convert HTML or markdown to PDF (base64 output) |\n| `kyaoracle` | $0.005 | On-chain trust score (0–100) for an Ethereum/Base wallet address |\n| `linkrisk` | $0.005 | URL risk profile — heuristic phishing signals, redirect tracing |\n| `markdownopt` | $0.005 | Convert URL or HTML to clean LLM-ready markdown (~70% token reduction) |\n| `notifyrelay_email` | $0.005 | Send a transactional email via Resend (allowlisted, rate-limited) |\n| `embedpay` | $0.00005 / 1k tokens | OpenAI text-embedding-3-small wrapper, batch tier available |\n| `linksafe` | $0.01 | Definitive URL safety check via Playwright sandbox + VirusTotal |\n| `scrapepay` | $0.01 | Web extraction via Playwright (robots.txt enforced, SSRF-safe) |\n| `pdf_render` | $0.49 | High-fidelity URL or HTML → PDF via Playwright |\n\n22 services. Live prices and live wallet [on Basescan](https://basescan.org/address/0x1C680703D6cF7dfC9FEABb5AA28E64B869ddB3bC#tokentxns).\n\n---\n\n## Why x402, why pay-per-call\n\n- **No signup tax.** Every tool here works the moment your wallet has USDC. No accounts to provision, no API keys to rotate, no subscription tiers to forecast.\n- **Charge-on-success-only.** Every service settles payment only on HTTP 2xx with non-empty content. Failed calls cost nothing — your retry budget is preserved.\n- **Composes naturally.** ScrapePay → MarkdownOpt → EmbedPay → MemoryServe → MEMSCRUB is the canonical RAG pipeline. Each step's payment is independent and verifiable on-chain.\n- **MCP-native.** One install, all 22 tools appear in Claude Desktop, Cursor, Cline, Continue, Claude Code, or any MCP-aware agent runtime.\n- **No vendor lock-in.** x402 is a Linux Foundation protocol (April 2026) co-signed by Google, AWS, Stripe, Visa, Mastercard. Other providers will offer x402 services; your wallet client works with all of them.\n\n---\n\n## Installation — Claude Desktop\n\nAdd to your `claude_desktop_config.json`:\n\n```json\n{\n  \"mcpServers\": {\n    \"x402-tools\": {\n      \"command\": \"npx\",\n      \"args\": [\"@melis-ai/x402-tools-mcp\"]\n    }\n  }\n}\n```\n\nmacOS: `~/Library/Application Support/Claude/claude_desktop_config.json`\nWindows: `%APPDATA%\\Claude\\claude_desktop_config.json`\n\nRestart Claude Desktop. All 22 tools appear in the tool picker.\n\n## Installation — Cursor, Cline, Continue, Claude Code\n\nSee [agents.melis.ai/docs/install-mcp](https://agents.melis.ai/docs/install-mcp) for per-client setup.\n\n---\n\n## Example: canonical RAG pipeline\n\n```typescript\n// All 22 tools registered as MCP tools — your agent calls them like any function\nconst page    = await callTool('scrapepay',   { url: 'https://example.com/article' });\nconst md      = await callTool('markdownopt', { html: page.content });\nconst vec     = await callTool('embedpay',    { input: md.markdown });\nconst stored  = await callTool('memoryserve_write', {\n  agent_id: 'agent-1', content: md.markdown, vector: vec.embedding,\n});\n\n// Later — recall and guard against indirect injection\nconst hits    = await callTool('memoryserve_query', {\n  agent_id: 'agent-1', query: 'what did we learn about X?',\n});\nfor (const chunk of hits.matches) {\n  const scrub = await callTool('memscrub', { content: chunk.content });\n  if (scrub.risk_level === 'safe') useChunk(chunk);\n}\n```\n\nTotal cost per 5k-token page: ~$0.017 USDC. Detailed walkthrough: [agents.melis.ai/pipelines/rag](https://agents.melis.ai/pipelines/rag).\n\n---\n\n## Funding the wallet\n\nx402 settles in USDC on Base (Coinbase L2). Two paths:\n\n- **Coinbase Wallet** — buy USDC, switch to Base network, send to your agent's wallet.\n- **Bridge from Ethereum mainnet** — [bridge.base.org](https://bridge.base.org).\n\n$1.00 of USDC covers 100 ScrapePay calls, 200 PromptGuard calls, or one full RAG-pipeline ingestion run.\n\n---\n\n## Discovery surfaces (for agent builders + AI consumers)\n\n| URL | Purpose |\n|-----|---------|\n| [agents.melis.ai/llms.txt](https://agents.melis.ai/llms.txt) | Concise LLM-readable catalogue |\n| [agents.melis.ai/llms-full.txt](https://agents.melis.ai/llms-full.txt) | Full schemas + composition recipes |\n| [agents.melis.ai/openapi.json](https://agents.melis.ai/openapi.json) | OpenAPI 3.1 spec for all 22 endpoints |\n| [agents.melis.ai/ai-plugin.json](https://agents.melis.ai/ai-plugin.json) | ChatGPT-plugin manifest |\n| `https://<service>.melis.ai/.well-known/mcp.json` | Per-service MCP discovery |\n| [agents.melis.ai/agents-faq](https://agents.melis.ai/agents-faq) | Agent-builder FAQ (distinct from human FAQ) |\n\n---\n\n## Comparisons\n\n- [ScrapePay vs Firecrawl](https://agents.melis.ai/comparison/vs-firecrawl)\n- [EmbedPay vs OpenAI Embeddings (direct)](https://agents.melis.ai/comparison/vs-openai-embeddings)\n- [MemoryServe vs Pinecone](https://agents.melis.ai/comparison/vs-pinecone)\n- [Full alternatives doc](https://agents.melis.ai/docs/compare)\n\n---\n\n## Source & licensing\n\n- **MCP wrapper source** (this repo): MIT licensed.\n- **Service code** (the 22 services themselves): closed source for security.\n- **Site content** (agents.melis.ai docs): CC-BY-4.0 — attribute \"melis x402 Tools\" with a link to agents.melis.ai.\n\n---\n\n## Security\n\nFound a vulnerability? See [SECURITY.md](./SECURITY.md). Email mizukaizen@proton.me. Critical issues acknowledged within 24 hours.\n\n---\n\n## Citing this work\n\nIf you use melis x402 Tools in research or downstream products, see [CITATION.cff](./CITATION.cff) for the canonical citation.\n\n---\n\n## Author\n\n[mizukaizen](https://melis.ai) — agent operator and builder.\nCatalogue: [agents.melis.ai](https://agents.melis.ai) · Email: mizukaizen@proton.me\n",
  "bytes": 8376,
  "sha": "575e570322ea512edae59edae5feb73fd9dfa3e85886d2119e5ae23018d2529d",
  "repo_slug": "mizukaizen/x402-tools-mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_mizukaizen_x402_tools_mcp_348458a7/readme"
}