dev.workers.quynguyenbac.quickbuild/agent-tools

Est-ce que dev.workers.quynguyenbac.quickbuild/agent-tools est sûr ?

Au dernier audit MCP Hub, le serveur MCP « dev.workers.quynguyenbac.quickbuild/agent-tools » est classé « Non encore testé ». Référencé dans l'annuaire. Seul le pentest comportemental fait foi, et il n'a pas encore été exécuté sur ce serveur. Le verdict est réévalué en continu ; consultez la fiche pour l'état à jour.

Méthode : MCP Hub analyse la description de chaque outil (couche 1) et, pour le verdict fort, exécute le serveur dans une micro-VM isolée avec leurres et réseau bloqué (couche 2). On publie des noms et des compteurs, jamais le contenu brut renvoyé par un outil.

Les 9 outils

• free_site_check≈ 155 tokens

  [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).

  Paramètres, retour & exemple (1)

  Paramètres

  • url · string · requis
    Public http(s) URL or hostname to check.

  Exemple d'appel

  {"name": "free_site_check", "arguments": {"url": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• generate_image≈ 258 tokens

  [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.

  Paramètres, retour & exemple (2)

  Paramètres

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

  Exemple d'appel

  {"name": "generate_image", "arguments": {"steps": 1, "prompt": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• page_metadata≈ 205 tokens

  [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.

  Paramètres, retour & exemple (1)

  Paramètres

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

  Exemple d'appel

  {"name": "page_metadata", "arguments": {"url": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• screenshot_url≈ 495 tokens

  [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.

  Paramètres, retour & exemple (8)

  Paramètres

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

  Exemple d'appel

  {"name": "screenshot_url", "arguments": {"url": "texte", "type": "png", "width": 1, "height": 1, "waitMs": 1, "quality": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• summarize≈ 473 tokens

  [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).

  Paramètres, retour & exemple (6)

  Paramètres

  • url · string · optionnel
    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 · optionnel
    Optional output language for summary/keyPoints (ISO 639-1, e.g. "en"). Default: same as the content.
  • text · string · optionnel
    Raw text or Markdown to summarize instead of a URL (optional, max 200000 chars, first 24000 analyzed). Prefer POST for long text.
  • focus · string · optionnel
    Optional aspect to emphasize, e.g. "pricing", "API limits", "risks" (max 200 chars).
  • length · string · optionnel · short | medium | long
    Summary length: short = 1-2 sentences, medium = 3-4 (default), long = 5-8.
  • maxPoints · integer · optionnel
    Max number of keyPoints (default 5).

  Exemple d'appel

  {"name": "summarize", "arguments": {"url": "texte", "lang": "texte", "text": "texte", "focus": "texte", "length": "short", "maxPoints": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• text_to_speech≈ 281 tokens

  [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.

  Paramètres, retour & exemple (2)

  Paramètres

  • lang · string · optionnel · en | es | fr | zh | ja | ko
    Language of the text / voice (default en).
  • text · string · optionnel
    Text to speak (max 2000 chars). Optional: defaults to a short English sample.

  Exemple d'appel

  {"name": "text_to_speech", "arguments": {"lang": "en", "text": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• translate≈ 373 tokens

  [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.

  Paramètres, retour & exemple (5)

  Paramètres

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

  Exemple d'appel

  {"name": "translate", "arguments": {"to": "texte", "url": "texte", "from": "texte", "text": "texte", "maxChars": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• url_to_markdown≈ 224 tokens

  [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).

  Paramètres, retour & exemple (2)

  Paramètres

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

  Exemple d'appel

  {"name": "url_to_markdown", "arguments": {"url": "texte", "maxChars": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• website_audit≈ 180 tokens

  [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.

  Paramètres, retour & exemple (1)

  Paramètres

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

  Exemple d'appel

  {"name": "website_audit", "arguments": {"url": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

C'est votre serveur ?

Revendiquez-le sur l'espace créateur (preuve GitHub, domaine ou npm) pour afficher le badge « propriétaire vérifié » et lancer un pentest comportemental à la demande afin d'obtenir le badge « Vérifié ».

Créer un compte / revendiquer →

Source

https://quickbuild.quynguyenbac.workers.dev/mcp