X402 Tools Mcp

io.github.mizukaizenPublished by GitHub account mizukaizenv0.1.4Updated Oct 24, 2026

melis x402 Tools — 22 pay-per-call APIs for AI agents. No accounts, no API keys. USDC on Base.

VerifiedSTDIODesktop onlyWeb Search & Scraping Knowledge & Memory Developer Tools

Server details

Identifier: io.github.mizukaizen/x402-tools-mcp
Transport: STDIO
Runtime: Desktop only
Trust: Verified
Published: Sep 16, 2026

Security note

MCP servers receive tool arguments from a conversation and may perform external actions. Review what a server can do before you enable it, and give it only the access it needs.

The registry verified the GitHub account mizukaizen for this listing. That does not show the account is the product's maker.

SourceWeft's checks cover whether the listing is complete and the endpoint answered; they do not review the server's code or what its tools do.

Add a badge to your README

Show readers this MCP server is listed on SourceWeft. The badge links to this page.

[![Listed on SourceWeft](https://sourceweft.com/badge/mcp/io.github.mizukaizen%2Fx402-tools-mcp.svg)](https://sourceweft.com/mcp/io.github.mizukaizen%2Fx402-tools-mcp?utm_source=readme&utm_medium=badge)

Overview

AI-generated overview

A local MCP server exposing 22 pay-per-call utility APIs — scraping, conversion, embeddings, memory, moderation and notifications — paid in USDC on Base via x42

What you can do: Fetch and extract web content, convert documents and render PDFs, and turn pages into clean markdown for LLM use (cacheserve, scrapepay, structextract, markdownopt, docconvert_text, docconvert_pdf, pdf_render). Store and recall agent memories with embeddings, and relay context between agents (memoryserve_write, memoryserve_query, embedpay, intentflow). Screen untrusted input and links for prompt injection, phishing and unsafe images (promptguard, memscrub, linkrisk, linksafe, imageguard). Validate JSON against schemas, sign audit certificates, and check wallet trust scores (schemagate, xaudit, kyaoracle). Send webhooks, Telegram messages and transactional email (notifyrelay_webhook, notify_
When to use it: Useful when an agent needs ready-made building blocks — scraping, embeddings, memory, moderation, notifications — without signing up for separate provider accounts, and when you are willing to fund a crypto wallet and pay small per-call fees.
Requirements: Runs locally via npx with Node.js, configured in an MCP client such as Claude Desktop. A wallet client holding USDC on the Base network is needed to pay per call; no accounts or API keys are required. Optional secrets X402_INTERNAL_KEY and X402_PAYMENT_HEADER exist for bypassing or handling payments manually.

Before you install

Every tool call spends real USDC from your wallet, with prices from about $0.00005 to $0.49 per call; failed calls are said to settle only on success. The X402_INTERNAL_KEY bypass key and X402_PAYMENT_HEADER payment token are secrets. Tools send data to third parties: URLs to scraping and VirusTotal checks, content to embedding and moderation services, and messages or emails to recipients. The 22 services are closed source.

Installation

In SourceWeft

Open X402 Tools Mcp in the dashboard and add it to a workspace.
Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

@melis-ai/x402-tools-mcp

[npm version] [License: MIT] [MCP compatible] [x402] [Catalogue]

Boring 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.

→ Full catalogue with prices and live examples: agents.melis.ai → Canonical 5-step RAG pipeline: agents.melis.ai/pipelines/rag → 5-minute getting started: agents.melis.ai/docs/getting-started

Tool catalogue (22)

Tool	Price (USDC)	Description
`list_services`	free	Returns the full catalogue with prices and endpoint URLs
`cacheserve`	$0.001	Fetch a URL with server-side caching — avoids redundant origin hits
`docconvert_text`	$0.001	Format conversion: md↔html, json↔csv, html→txt, etc.
`intentflow`	$0.001	Context handoff relay for multi-agent delegation (async, returns retrieve_url)
`memoryserve_write`	$0.001	Store text + embedding in Qdrant + SQLite, namespaced per `agent_id`
`memoryserve_query`	$0.001	Recall most-similar memories by semantic query
`memscrub`	$0.001	Scan retrieved RAG content for indirect prompt injection (10 patterns)
`notifyrelay_webhook`	$0.001	POST a JSON payload to a URL with optional HMAC-SHA256 signing
`schemagate`	$0.001	Validate a JSON response against a JSON Schema, return a hint on failure
`loopwall_hop`	$0.0005	Validate one hop of a signed multi-agent chain (loop / budget enforcement)
`loopwall_issue`	$0.001	Issue a signed Job Envelope at chain start with budget + hop cap
`imageguard`	$0.002	NSFW image classification (multi-class moderation on roadmap)
`notifyrelay_telegram`	$0.002	Send a Telegram message to a known chat ID
`promptguard`	$0.002	Score untrusted input for prompt injection risk (0–100)
`structextract`	$0.002	Extract structured JSON from HTML — tables, links, emails, phones
`xaudit`	$0.002	Validate API response content with a cryptographically signed certificate
`docconvert_pdf`	$0.005	Convert HTML or markdown to PDF (base64 output)
`kyaoracle`	$0.005	On-chain trust score (0–100) for an Ethereum/Base wallet address
`linkrisk`	$0.005	URL risk profile — heuristic phishing signals, redirect tracing
`markdownopt`	$0.005	Convert URL or HTML to clean LLM-ready markdown (~70% token reduction)
`notifyrelay_email`	$0.005	Send a transactional email via Resend (allowlisted, rate-limited)
`embedpay`	$0.00005 / 1k tokens	OpenAI text-embedding-3-small wrapper, batch tier available
`linksafe`	$0.01	Definitive URL safety check via Playwright sandbox + VirusTotal
`scrapepay`	$0.01	Web extraction via Playwright (robots.txt enforced, SSRF-safe)
`pdf_render`	$0.49	High-fidelity URL or HTML → PDF via Playwright

22 services. Live prices and live wallet on Basescan.

Why x402, why pay-per-call

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.
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.
Composes naturally. ScrapePay → MarkdownOpt → EmbedPay → MemoryServe → MEMSCRUB is the canonical RAG pipeline. Each step's payment is independent and verifiable on-chain.
MCP-native. One install, all 22 tools appear in Claude Desktop, Cursor, Cline, Continue, Claude Code, or any MCP-aware agent runtime.
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.

Installation — Claude Desktop

Add to your claude_desktop_config.json:

json

{  "mcpServers": {    "x402-tools": {      "command": "npx",      "args": ["@melis-ai/x402-tools-mcp"]    }  }}

{  "mcpServers": {    "x402-tools": {      "command": "npx",      "args": ["@melis-ai/x402-tools-mcp"]    }  }}

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json Windows: %APPDATA%\Claude\claude_desktop_config.json

Restart Claude Desktop. All 22 tools appear in the tool picker.

Installation — Cursor, Cline, Continue, Claude Code

See agents.melis.ai/docs/install-mcp for per-client setup.

Example: canonical RAG pipeline

typescript

// All 22 tools registered as MCP tools — your agent calls them like any functionconst page    = await callTool('scrapepay',   { url: 'https://example.com/article' });const md      = await callTool('markdownopt', { html: page.content });const vec     = await callTool('embedpay',    { input: md.markdown });const stored  = await callTool('memoryserve_write', {  agent_id: 'agent-1', content: md.markdown, vector: vec.embedding,});
// Later — recall and guard against indirect injectionconst hits    = await callTool('memoryserve_query', {  agent_id: 'agent-1', query: 'what did we learn about X?',});for (const chunk of hits.matches) {  const scrub = await callTool('memscrub', { content: chunk.content });  if (scrub.risk_level === 'safe') useChunk(chunk);}

// All 22 tools registered as MCP tools — your agent calls them like any functionconst page    = await callTool('scrapepay',   { url: 'https://example.com/article' });const md      = await callTool('markdownopt', { html: page.content });const vec     = await callTool('embedpay',    { input: md.markdown });const stored  = await callTool('memoryserve_write', {  agent_id: 'agent-1', content: md.markdown, vector: vec.embedding,});
// Later — recall and guard against indirect injectionconst hits    = await callTool('memoryserve_query', {  agent_id: 'agent-1', query: 'what did we learn about X?',});for (const chunk of hits.matches) {  const scrub = await callTool('memscrub', { content: chunk.content });  if (scrub.risk_level === 'safe') useChunk(chunk);}

Total cost per 5k-token page: ~$0.017 USDC. Detailed walkthrough: agents.melis.ai/pipelines/rag.

Funding the wallet

x402 settles in USDC on Base (Coinbase L2). Two paths:

Coinbase Wallet — buy USDC, switch to Base network, send to your agent's wallet.
Bridge from Ethereum mainnet — bridge.base.org.

$1.00 of USDC covers 100 ScrapePay calls, 200 PromptGuard calls, or one full RAG-pipeline ingestion run.

Discovery surfaces (for agent builders + AI consumers)

URL	Purpose
agents.melis.ai/llms.txt	Concise LLM-readable catalogue
agents.melis.ai/llms-full.txt	Full schemas + composition recipes
agents.melis.ai/openapi.json	OpenAPI 3.1 spec for all 22 endpoints
agents.melis.ai/ai-plugin.json	ChatGPT-plugin manifest
`https://<service>.melis.ai/.well-known/mcp.json`	Per-service MCP discovery
agents.melis.ai/agents-faq	Agent-builder FAQ (distinct from human FAQ)

Comparisons

Source & licensing

MCP wrapper source (this repo): MIT licensed.
Service code (the 22 services themselves): closed source for security.
Site content (agents.melis.ai docs): CC-BY-4.0 — attribute "melis x402 Tools" with a link to agents.melis.ai.

Security

Found a vulnerability? See SECURITY.md. Email [email protected]. Critical issues acknowledged within 24 hours.

Citing this work

If you use melis x402 Tools in research or downstream products, see CITATION.cff for the canonical citation.

Author

mizukaizen — agent operator and builder. Catalogue: agents.melis.ai · Email: [email protected]

Source: README.md at commit 8167a35

Tools

SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

v0.1.4LatestSep 16, 2026

Score

40% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

Reached in the last 30 days25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
Auth declared10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
DescriptionRequired15 pts
Logo10 pts
Documentation15 pts
License10 pts
Declare a license in the repository or the registry entry.