QuickBuild agent tools (x402)

Measured conclusion: Deep-tested. L2 outcome: tools_ok.

Screenshot, TTS, image gen, translate, summarize, URL-to-Markdown, site audit. Pay per call (x402).

Add to your agent

Copy this into your MCP client config:

{
  "mcpServers": {
    "QuickBuild agent tools (x402)": {
      "url": "https://quickbuild.quynguyenbac.workers.dev/mcp",
      "transport": "streamable-http"
    }
  }
}

Measured tools (19)

• launchcheck_full read-only

  [PAID $0.05 USDC per call via x402 on Base; errors are free] LaunchCheck full report for one public URL: status code, HTTPS/redirects, title/description, Open Graph/Twitter card, robots.txt/sitemap/noindex, plus up to 50 links checked for breakage, og:image load check, desktop 1280x800 and mobile 390x844 JPEG screenshots, edge TTFB and real-browser load time, image alt text, heading outline, mobile overflow, and a P1-P3 prioritized fix list. Read-only. Unreachable sites are not charged.

  Parameters:

  • url — string — Public http(s) URL (hostname, not IP). Private/reserved addresses are refused. Optional: defaults to https://example.com.

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• website_audit read-only

  [PAID $0.05 USDC per call via x402 on Base; errors are free] Pre-launch website audit: up to 3 pages crawled, 30 links checked, meta/OG/canonical, security headers, HTTPS, 404 handling, sitemap, and leaked-secret patterns in client JS (masked). Read-only.

  Parameters:

  • url — string — Public http(s) URL (hostname, not IP). Private/reserved addresses are refused. Optional: defaults to https://example.com.

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• page_metadata read-only

  [PAID $0.005 USDC per call via x402 on Base; errors are free] Fetch one public web page and return structured metadata: title, meta description, canonical, lang, robots, Open Graph and Twitter card tags, favicon, RSS/Atom feeds, JSON-LD @types, and internal/external links (up to 100 each). Good for link previews, unfurling and quick site triage.

  Parameters:

  • url — string — Public http(s) URL (hostname, not IP). Private/reserved addresses are refused. Optional: defaults to https://example.com.

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• url_to_markdown read-only

  [PAID $0.005 USDC per call via x402 on Base; errors are free] Fetch one public web page and return its main content (article/main/body, scripts/nav/footer stripped) as clean Markdown with absolute links, plus title and length. Up to 2 MB HTML, 10 s timeout; optional maxChars (default 50000, max 200000).

  Parameters:

  • url — string — Public http(s) URL (hostname, not IP). Private/reserved addresses are refused. Optional: defaults to https://example.com.
  • maxChars — integer — Truncate markdown to this many characters (default 50000)

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• summarize read-only

  [PAID $0.02 USDC per call via x402 on Base; errors are free] Fetch a public web page (or take raw text) and return a structured JSON brief made by Llama 3.3 70B: title, language, contentType, summary, keyPoints, named entities with types, topic tags, concrete facts (prices, dates, versions, limits) as label/value pairs, sentiment and audience. Grounded in the page only, no invented facts. Reads up to 24,000 chars of main content (2 MB HTML, 10 s fetch timeout). All params optional: with none it summarizes https://example.com. GET with query params, or POST a JSON body for long text (up to 200,000 chars accepted, first 24,000 analyzed).

  Parameters:

  • url — string — Public http(s) URL to read (hostname, not IP; private addresses refused). Optional: defaults to https://example.com. Ignored when `text` is given.
  • lang — string — Optional output language for summary/keyPoints (ISO 639-1, e.g. "en"). Default: same as the content.
  • text — string — Raw text or Markdown to summarize instead of a URL (optional, max 200000 chars, first 24000 analyzed). Prefer POST for long text.
  • focus — string — Optional aspect to emphasize, e.g. "pricing", "API limits", "risks" (max 200 chars).
  • length — string — Summary length: short = 1-2 sentences, medium = 3-4 (default), long = 5-8.
  • maxPoints — integer — Max number of keyPoints (default 5).

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• translate read-only

  [PAID $0.005 USDC per call via x402 on Base; errors are free] LLM translation (Meta Llama 4 Scout on Workers AI, M2M100 fallback). Give `text`, or a `url` whose main content is extracted as Markdown and translated in blocks, preserving Markdown formatting, URLs and code blocks. Source language auto-detected (or set `from`). Up to 20,000 chars per call (default 8,000). All params optional: with none it translates a short Spanish sample to English. Languages: en,es,fr,de,it,pt,nl,ru,uk,pl,cs,ro,hu,el,bg,sv,da,no,fi,tr,ar,he,fa,hi,bn,ur,ta,zh,ja,ko,vi,th,id,ms,tl,sw.

  Parameters:

  • to — string — Target language, ISO 639-1 code or English name (default "en").
  • url — string — Public http(s) URL whose main content is translated (optional; used when `text` is absent).
  • from — string — Source language code, or "auto" (default: auto-detect).
  • text — string — Text or Markdown to translate (optional). If omitted and no url, a short Spanish sample is used.
  • maxChars — integer — Max source chars to translate (default 8000).

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• generate_image read-only

  [PAID $0.01 USDC per call via x402 on Base; errors are free] Generate an original 1024x1024 image from a text prompt with FLUX.1 [schnell] on Workers AI (about 2-5 s). Returns JSON with image_base64 + mimeType, or the raw image bytes with format=jpeg. Content policy: no sexual/nude, gore, hate, real or famous people, or ID documents/currency; such prompts get HTTP 400 and are not charged. All params optional: with no prompt a sample watercolor lighthouse is drawn.

  Parameters:

  • steps — integer — Diffusion steps, more = more detail (default 4).
  • prompt — string — What to draw (max 1000 chars). Optional: defaults to a watercolor lighthouse.

  Hints: read-only yes · destructive no · idempotent no · open-world yes

• screenshot_url read-only

  [PAID $0.008 USDC per call via x402 on Base; errors are free] Render a public web page in a real headless Chrome (JavaScript executed, waits for network idle) and return a screenshot: viewport (default 1280x800) or full page (up to 8000 px tall), PNG or JPEG, optional dark mode and extra wait. JSON with image_base64 + finalUrl/status/title, or raw image bytes with format=png|jpeg. Typically 2-6 s (up to ~25 s when busy). Use it for visual QA, link previews, archiving, checking what a page really shows, or feeding a vision model. Adult/malware domains (Cloudflare family DNS) and private addresses are refused. All params optional: with none it captures https://example.com. Errors are never charged.

  Parameters:

  • url — string — Public http(s) URL to capture (hostname, not IP). Optional: defaults to https://example.com.
  • type — string — Image type (default png).
  • width — integer — Viewport width in px (default 1280).
  • height — integer — Viewport height in px (default 800).
  • waitMs — integer — Extra wait after load before capturing, ms (default 0).
  • quality — integer — JPEG quality (default 80; jpeg only).
  • darkMode — boolean — Emulate prefers-color-scheme: dark (default false).
  • fullPage — boolean — Capture the whole scrollable page, capped at 8000 px tall (default false).

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• text_to_speech read-only

  [PAID $0.005 USDC per call via x402 on Base; errors are free] Turn text (up to 2000 chars) into spoken audio with MeloTTS on Cloudflare Workers AI, in English, Spanish, French, Chinese, Japanese or Korean. Returns JSON with audio_base64 + mimeType (audio/wav, 44.1 kHz mono), or the raw audio bytes with format=wav. Good for voice replies, narration, accessibility and language practice. Text with sexual, hateful or violent content is refused (HTTP 400, not charged). All params optional: with none it speaks a short English sample. GET with query params or POST a JSON body.

  Parameters:

  • lang — string — Language of the text / voice (default en).
  • text — string — Text to speak (max 2000 chars). Optional: defaults to a short English sample.

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• base_gas_price read-only

  [PAID $0.001 USDC per call via x402 on Base; errors are free] Live gas snapshot for Base mainnet (chain 8453) read from public Base RPC: latest block number/time/utilization, base fee, eth_gasPrice, eth_maxPriorityFeePerGas, the last 10 blocks of base fees, slow/standard/fast EIP-1559 fee suggestions (10th/50th/90th percentile tips) in gwei and wei, and the estimated total cost (L2 execution + OP Stack L1 data-fee upper bound) of an ETH transfer, an ERC-20 transfer and a swap in ETH and USD (Chainlink ETH/USD on Base). No params. Cached 4 s. Errors are never charged.

  Hints: read-only yes · destructive no · idempotent no · open-world yes

• base_wallet_balances read-only

  [PAID $0.002 USDC per call via x402 on Base; errors are free] Balances of one address on Base mainnet in a single call: native ETH, the well-known tokens USDC, USDT, USDbC, DAI, WETH, cbETH, wstETH, AERO (non-zero only, or all with includeZero=true), plus up to 10 extra ERC-20 contracts you pass in `tokens` (symbol/name/decimals read on-chain). Also nonce, account type (EOA, EIP-7702 delegated EOA, or contract) and a USD total for ETH/WETH (Chainlink) and stablecoins. Read live from public Base RPC via Multicall3; cached 10 s. All params optional: defaults to a well-known public address. Invalid input = 400, never charged.

  Parameters:

  • tokens — string — Optional comma-separated extra ERC-20 contract addresses on Base (max 10).
  • address — string — Base address (0x + 40 hex). Optional: defaults to 0xd8dA6BF26964aF9D7eEd9e03E53415D37aA96045 (vitalik.eth).
  • includeZero — boolean — Also list well-known tokens with zero balance (default false).

  Hints: read-only yes · destructive no · idempotent no · open-world yes

• base_token_info read-only

  [PAID $0.002 USDC per call via x402 on Base; errors are free] Inspect a token or any address on Base mainnet: contract vs EOA (incl. EIP-7702 delegation), bytecode size, ERC-20 name/symbol/decimals/totalSupply (raw and formatted; bytes32 symbols handled), proxy implementation (EIP-1967, beacon, ZeppelinOS/FiatToken), whether it is a well-known Base token (guards against spoofed symbols), and optionally the balance of `holder`. Read live from public Base RPC; metadata cached 1 h. All params optional: defaults to USDC on Base. Invalid input = 400, never charged.

  Parameters:

  • holder — string — Optional address whose balance of this token to include.
  • address — string — Token / contract address on Base (0x + 40 hex). Optional: defaults to USDC 0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913.

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• base_tx_status read-only

  [PAID $0.002 USDC per call via x402 on Base; errors are free] Look up one transaction on Base mainnet by hash: status (success, failed or pending), block, timestamp, confirmations, from/to, value, method id, gas used, effective gas price, fee split into L2 execution and L1 data fee (ETH and USD), contract created, and decoded ERC-20 Transfer events (token, symbol, from, to, amount; up to 20). Useful to confirm a payment landed. Read live from public Base RPC. All params optional: defaults to a confirmed USDC x402 payment. Unknown hash = 404, invalid hash = 400, never charged.

  Parameters:

  • hash — string — Transaction hash (0x + 64 hex). Optional: defaults to 0x20215b4a54f0a39995f3afbd748d7b52c3a1922685ddf08e5f694ea1e89b52bf.

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• llm_chat read-only

  [PAID $0.003 USDC per call via x402 on Base; errors are free] One-shot LLM completion on Cloudflare Workers AI with a minimal interface: give `prompt` (and optionally `system`, or OpenAI-style `messages`), get {text, model, finish_reason, usage}. Models: llama-3.1-8b (default), llama-3.2-3b, llama-3.2-1b, mistral-7b, granite-4.0-micro. max_tokens capped at 512, input up to 24000 chars, Llama Guard 3 safety check, 503 "capacity" when the daily budget is used up. Errors are never charged. All params optional: with none it answers a short sample question. For the OpenAI wire format use POST /v1/chat/completions.

  Parameters:

  • model — string — Model alias (default llama-3.1-8b).
  • prompt — string — User message. Optional: defaults to a short sample question.
  • system — string — Optional system instruction.
  • messages — array — Optional OpenAI-style history (POST JSON).
  • max_tokens — integer — Max output tokens (default/cap 512).
  • temperature — number — Sampling temperature.

  Hints: read-only yes · destructive no · idempotent no · open-world yes

• text_embeddings read-only

  [PAID $0.001 USDC per call via x402 on Base; errors are free] Drop-in OpenAI Embeddings endpoint: POST {input: string | string[], model, encoding_format: float|base64, dimensions} and get {object: "list", data: [{embedding, index}], model, usage}. Models (Cloudflare Workers AI): bge-m3 (1024-d, multilingual (100+ languages), 8192-token context); bge-large-en-v1.5 (1024-d, English); bge-base-en-v1.5 (768-d, English); bge-small-en-v1.5 (384-d, English, fastest); embeddinggemma-300m (768-d, multilingual (Google EmbeddingGemma)). Any other model name (e.g. text-embedding-3-small) maps to bge-m3; the actual model is in the response. `dimensions` truncates and re-normalizes. Up to 100 inputs per call, 8000 chars each, 60000 chars total, one fixed price per call. For RAG, semantic search, clustering and dedupe. Errors are never charged. GET ?input= also works; with no params it embeds a sample sentence.

  Parameters:

  • input — ['string', 'array'] — Text or array of texts to embed (max 100). Optional: defaults to a sample sentence.
  • model — string — Embedding model alias (default bge-m3).
  • dimensions — integer — Optional output size; vectors are truncated and re-normalized.
  • encoding_format — string — float (default) or base64 (little-endian float32).

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• rerank_documents read-only

  [PAID $0.002 USDC per call via x402 on Base; errors are free] Cohere/Jina-style rerank: POST {query, documents: string[] | {text}[], top_n, return_documents} and get {results: [{index, relevance_score, document?}]} sorted by relevance. Models (Cloudflare Workers AI): bge-reranker-base (cross-encoder, English/Chinese, scores 0..1); bge-m3 (multilingual similarity scoring) (default bge-reranker-base; other names map to it). Up to 100 documents, each scored on its first 4000 chars; one fixed price per call. Use after vector search to pick the best passages for an LLM. Errors are never charged. All params optional: with none it ranks a small sample.

  Parameters:

  • model — string — Rerank model (default bge-reranker-base).
  • query — string — Search query (max 2000 chars). Optional with documents omitted: a sample is ranked.
  • top_n — integer — Return only the best N (default all).
  • documents — array — Documents to rank: strings or {text} objects (max 100).
  • return_documents — boolean — Include the document text in each result (default false).

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• crypto_price read-only

  [PAID $0.001 USDC per call via x402 on Base; errors are free] Live crypto prices for up to 25 coins per call: pass tickers in `symbols` (BTC,ETH,SOL,AERO,...; common tickers built in, others resolved by CoinGecko search to the largest coin with that ticker), CoinGecko `ids`, or one token `address` + `chain` (base default; ethereum, arbitrum, optimism, polygon, bsc, avalanche, solana). Returns price, market cap, 24h volume and 24h % change in each `vs` currency (usd default; up to 5, e.g. usd,eur,btc) plus last-updated time. Data: CoinGecko public API, cached 30 s; falls back to Coinbase spot rates (price only) if CoinGecko is unavailable. All params optional: with none it returns BTC and ETH in USD. Unknown coins = 404, invalid input = 400, never charged.

  Parameters:

  • vs — string — Comma-separated quote currencies (max 5), e.g. usd,eur,btc. Default usd.
  • ids — string — Comma-separated CoinGecko coin ids, e.g. bitcoin,aerodrome-finance (optional).
  • chain — string — Chain of `address` (default base).
  • address — string — Optional token contract address; returns that token price (overrides symbols/ids).
  • symbols — string — Comma-separated tickers, e.g. BTC,ETH,SOL (max 25). Optional: defaults to BTC,ETH.

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• fx_rate read-only

  [PAID $0.002 USDC per call via x402 on Base; errors are free] Foreign-exchange rates from one base currency (`from`, default USD) to a list of currencies (`to`, comma-separated, or "all"; default 14 majors incl. EUR, GBP, JPY, CNY, INR, KRW, VND), with `amount` converted. Live mode uses Coinbase public exchange rates (updated about every minute, 160+ ISO 4217 currencies plus XAU/XAG), falling back to exchangerate-api daily rates. With `date=YYYY-MM-DD` it returns the ECB reference rates for that day (Frankfurter, ~30 major currencies, back to 1999-01-04). All params optional: with none it returns USD to 14 major currencies. Invalid codes = 400, never charged.

  Parameters:

  • to — string — Comma-separated target codes (max 50) or "all". Default: EUR,GBP,JPY,CNY,CHF,CAD,AUD,INR,KRW,SGD,HKD,MXN,BRL,VND.
  • date — string — Optional YYYY-MM-DD for historical ECB reference rates (since 1999-01-04). Omit for live rates.
  • from — string — Base currency, ISO 4217 code (default USD).
  • amount — number — Amount in `from` to convert (default 1).

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• free_site_check read-only

  [FREE, 10 calls/hour per IP] Quick check of one public website: homepage meta/OG/canonical, security headers, HTTPS, and up to 20 links tested for breakage. For the deeper 3-page audit with leaked-key scan use website_audit (paid).

  Parameters:

  • url (required) — string — Public http(s) URL or hostname to check.

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

Publisher website

Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.