Combien d'outils expose io.github.jkresearch8/domscout ?

io.github.jkresearch8/domscout expose 10 outil(s). Le coût de contexte pour les charger tous est d'environ 3112 tokens (coût unique au chargement, pas par appel).

accueil / serveurs / Fichiers & Documents / io.github.jkresearch8/domscout

io.github.jkresearch8/domscout

serveur MCP (Model Context Protocol)

▸ Fichiers & Documents

[ Vérifié ]

Verdict MCP Hub
Aucun comportement malveillant détecté au test comportemental.

npmType / transport

directAccès

~3112 tokensCoût de contexte

10Outils

Est-ce que io.github.jkresearch8/domscout est sûr ?

Au dernier audit MCP Hub, le serveur MCP « io.github.jkresearch8/domscout » est classé « Vérifié ». Aucun comportement malveillant détecté au test comportemental. 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.

Versions auditées & empreintes

Vérifiez la version que vous utilisez : son empreinte doit correspondre à celle listée ici — sinon vous n'utilisez pas la version auditée.

[ Vérifié ] v1.0.8 audité le 2026-10-21

sha512-Cf3uQkpWDn0kTn8Lv5yW2vV3Rg4nC7eJrpcEcauPb8/+m9tpt3IWEqyN4RHniRJ4AZ6jTV94GmeQxejnPXubcg==

npm view @domscout/mcp@1.0.8 dist.integrity

Vous utilisez ce serveur ? Suivez-le (créez un compte) pour être alerté dès qu'une nouvelle version paraît ou que le verdict change.

Les 10 outils

domscout_check_credits≈ 119 tokens
Free — this call never consumes credits or quota. Returns the credit balance, this month's quota usage, the per-second rate limit, and the full price list for every capture option. Call this before a large run to budget it, and after a 429 to find out whether you were rate limited (retry in a second) or are out of credits (do not retry).
Paramètres, retour & exemple (0)
Exemple d'appel
```
{"name": "domscout_check_credits", "arguments": {}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}]}
```
domscout_extract_markdown≈ 464 tokens
Costs 1 credit. Loads a page and returns its main content as clean Markdown, with the title, description, Open Graph fields, word count, an estimated token count, and a content-quality flag. This is the right tool for reading a page — it is the cheapest option and returns text rather than an image. Use domscout_capture_screenshot only when you actually need to SEE the page. Set fast:true for static pages (documentation, blogs, news, changelogs): same price, same result shape, roughly an order of magnitude faster, but it does not run JavaScript. Check meta.renderJs and meta.contentQuality in the result and retry without fast:true if the page came back thin.
Paramètres, retour & exemple (5)
Paramètres
- url · string · requis
  The page to load. Must be http(s) and publicly reachable. Credentials in the URL (https://user:pass@host) are rejected; these tools capture as an anonymous visitor, so use the REST API directly if the page needs authentication.
- fast · boolean · optionnel
  Skip the browser and read the served HTML directly. Much faster and the same price, but JavaScript does not run, so a client-rendered page may come back empty. Cannot be combined with waitForSelector or delay, which need a live page.
- delay · integer · optionnel
  Extra milliseconds to wait after load.
- lazyScroll · boolean · optionnel
  Scroll the page first to trigger lazy-loaded content. Adds 1 credit. Needs a browser, so it cannot be combined with fast:true.
- waitForSelector · string · optionnel
  Wait for this CSS selector to appear before capturing.
Exemple d'appel
```
{"name": "domscout_extract_markdown", "arguments": {"url": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}]}
```
domscout_capture_screenshot≈ 505 tokens
Costs 1 credit for a viewport PNG/JPEG/WebP; +1 for fullPage, +1 for PDF. Returns the image itself. Use this when you need to see layout, styling, or a visual state — for reading text, domscout_extract_markdown is cheaper and more useful.
Paramètres, retour & exemple (11)
Paramètres
- url · string · requis
  The page to load. Must be http(s) and publicly reachable. Credentials in the URL (https://user:pass@host) are rejected; these tools capture as an anonymous visitor, so use the REST API directly if the page needs authentication.
- delay · integer · optionnel
  Extra milliseconds to wait after load.
- width · integer · optionnel
  Viewport width in CSS pixels.
- format · string · optionnel · png | jpeg | webp | pdf
  PDF requires a Pro plan or above.
- height · integer · optionnel
  Viewport height in CSS pixels.
- quality · integer · optionnel
  JPEG/WebP quality.
- fullPage · boolean · optionnel
  Capture the whole scrollable page. Requires Pro or above. Adds 1 credit.
- selector · string · optionnel
  Capture only this element.
- devicePreset · string · optionnel · desktop | iphone13 | pixel7 | ipad
  Preset viewport and device characteristics. Overrides width/height when set.
- hideSelectors · array · optionnel
  Elements to hide before capturing, e.g. cookie banners.
- waitForSelector · string · optionnel
  Wait for this CSS selector to appear before capturing.
Exemple d'appel
```
{"name": "domscout_capture_screenshot", "arguments": {"url": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}]}
```
domscout_extract_data≈ 443 tokens
Costs 2 credits. Pulls named fields off a page using CSS selectors and returns typed JSON. Each field reports found/missing/invalid_selector separately, so a partial result tells you which selector was wrong rather than failing the whole call. Requires Pro or above.
Paramètres, retour & exemple (4)
Paramètres
- url · string · requis
  The page to load. Must be http(s) and publicly reachable. Credentials in the URL (https://user:pass@host) are rejected; these tools capture as an anonymous visitor, so use the REST API directly if the page needs authentication.
- delay · integer · optionnel
  Extra milliseconds to wait after load.
- fields · object · requis
  Field name → { selector, type, attribute?, all? }. type is one of text, number, boolean, attribute, html, url, list. Set all:true to collect every match instead of the first. At most 100 fields.
- waitForSelector · string · optionnel
  Wait for this CSS selector to appear before capturing.
Exemple d'appel
```
{"name": "domscout_extract_data", "arguments": {"url": "texte", "fields": {}}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}]}
```
domscout_inspect_page≈ 290 tokens
Costs 2 credits. Returns a semantic snapshot: the accessibility tree, the interactive elements, and a selector for each. Use this before domscout_automate_page to find out what is on the page and what to target. Requires Pro or above.
Paramètres, retour & exemple (5)
Paramètres
- url · string · requis
  The page to load. Must be http(s) and publicly reachable. Credentials in the URL (https://user:pass@host) are rejected; these tools capture as an anonymous visitor, so use the REST API directly if the page needs authentication.
- delay · integer · optionnel
  Extra milliseconds to wait after load.
- detail · string · optionnel · summary | full
  "full" is slower and always returns asynchronously.
- maxNodes · integer · optionnel
- waitForSelector · string · optionnel
  Wait for this CSS selector to appear before capturing.
Exemple d'appel
```
{"name": "domscout_inspect_page", "arguments": {"url": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}]}
```
domscout_automate_page≈ 557 tokens
Costs 1 credit, +1 if more than 10 steps. Runs a sequence of actions — click, type, select, scroll, wait, navigate, pressKey, assert — and returns the final page plus a per-step pass/fail report. Call domscout_inspect_page first to find selectors. Requires Pro or above. The whole sequence shares a 24-second budget.
Paramètres, retour & exemple (4)
Paramètres
- url · string · requis
  The page to load. Must be http(s) and publicly reachable. Credentials in the URL (https://user:pass@host) are rejected; these tools capture as an anonymous visitor, so use the REST API directly if the page needs authentication.
- actions · array · requis
  Up to 25 steps, run in order.
- screenshot · boolean · optionnel
  Return an image of the final state.
- extractMarkdown · boolean · optionnel
  Return the final page as Markdown.
Exemple d'appel
```
{"name": "domscout_automate_page", "arguments": {"url": "texte", "actions": []}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}]}
```
domscout_crawl_site≈ 300 tokens
Costs 1 credit per page crawled — submitting the crawl itself is free. Returns a job ID immediately — poll it with domscout_get_job. Always respects robots.txt (this cannot be disabled), caps at 500 pages and depth 5, and requires an explicit HTTPS allowedOrigins list. Requires a Business plan or above.
Paramètres, retour & exemple (7)
Paramètres
- seedUrl · string · requis
  Where to start. Must be https.
- maxDepth · integer · optionnel
- maxPages · integer · optionnel
- allowedOrigins · array · requis
  Bare https origins the crawl may visit, e.g. "https://example.com". Must include the seed origin.
- excludePatterns · array · optionnel
- extractMarkdown · boolean · optionnel
  Capture each page as Markdown.
- includePatterns · array · optionnel
Exemple d'appel
```
{"name": "domscout_crawl_site", "arguments": {"seedUrl": "texte", "allowedOrigins": []}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}]}
```
domscout_get_job≈ 172 tokens
Free — this call never consumes credits or quota. Poll a job ID returned by a crawl, a batch, or an auto-promoted capture. Status is one of pending, processing, retrying, done, error, cancel_requested, cancelled. Polling is free, so poll as often as you like — but the per-second rate limit still applies.
Paramètres, retour & exemple (2)
Paramètres
- kind · string · optionnel · job | batch | crawl
  Which endpoint to poll. Use "crawl" for a crawl job.
- jobId · string · requis
  The job ID.
Exemple d'appel
```
{"name": "domscout_get_job", "arguments": {"jobId": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}]}
```
domscout_cancel_job≈ 86 tokens
Free — this call never consumes credits or quota. Cooperatively cancels a durable job, batch, or crawl. Work already in flight may still complete.
Paramètres, retour & exemple (1)
Paramètres
- jobId · string · requis
Exemple d'appel
```
{"name": "domscout_cancel_job", "arguments": {"jobId": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}]}
```
domscout_send_feedback≈ 320 tokens
Free — this call never consumes credits or quota. — and it will never be charged, by design. Use this whenever something about this API got in your way: an error you could not act on, a parameter that did not behave as documented, a capability you needed and could not find, or a result that was wrong. Include the requestId from a failed call and the team sees exactly what happened on their side. A human reads these. Do not include API keys or other secrets.
Paramètres, retour & exemple (7)
Paramètres
- type · string · optionnel · bug | error_report | docs_gap | feature_request | praise | other
- actual · string · optionnel
- message · string · requis
  What happened, or what would have helped.
- endpoint · string · optionnel
  Which tool or endpoint, e.g. "domscout_extract_data".
- expected · string · optionnel
- severity · string · optionnel · blocking | major | minor | info
- requestId · string · optionnel
  The requestId from the call this is about, if there was one.
Exemple d'appel
```
{"name": "domscout_send_feedback", "arguments": {"message": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}]}
```

Badge pour votre README

Ce serveur a passé le pentest comportemental. Le badge porte son nom et renvoie à cette fiche — la preuve, c'est la fiche (verdict live qu'on contrôle), pas l'image.

Markdown

[![Vérifié par MCP Hub](https://dokore.fr/badge/io.github.jkresearch8--domscout.svg)](https://dokore.fr/serveur/io.github.jkresearch8--domscout)

HTML

<a href="https://dokore.fr/serveur/io.github.jkresearch8--domscout"><img src="https://dokore.fr/badge/io.github.jkresearch8--domscout.svg" alt="Vérifié par MCP Hub" height="20"></a>

Réévalué en continu : si le comportement change, le verdict tombe et le badge disparaît. Un badge qui ne pointe pas vers une fiche dokore.fr ne prouve rien. Comment ça marche

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

@domscout/mcp@1.0.8