dev.classifier/classifier

Est-ce que dev.classifier/classifier est sûr ?

Au dernier audit MCP Hub, le serveur MCP « dev.classifier/classifier » 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 5 outils

• classify_dimensions≈ 901 tokens

  Classify each text by several named dimensions, such as team, urgency and kind, in one request. Returns a label, confidence, scores and model for each field. At most 1,000 item × dimension decisions; every field counts toward the quota. Use per-dimension instructions to define ambiguous categories.

  Paramètres, retour & exemple (9)

  Paramètres

  • url · string · optionnel
    Scrape one public URL instead of inputs/items. Requires funded workspace access. Context.dev costs $0.0022 per billed attempt plus classification; long articles need Fast. Errors disclose retained charges. No automatic scrape retries.
  • tier · string · optionnel · fast | smart
    fast (default) or smart, which re-asks answers under 0.7 confidence of a reasoning model (slower, single-label only). Independent of the Laya processing lane.
  • items · array · optionnel
    1 to 1,000 texts to classify. Results come back in the same order.
  • model · string · optionnel · jev | laya | kev | chunklaya
  • include · array · optionnel
    With url: return article.markdown and/or article.html at no extra scrape cost. Omit for compact output.
  • dimensions · object · requis
    Named dimensions. Each is a label array or {labels, instructions}. At most 1,000 item × dimension decisions; definitions at most 16,000 characters combined.
  • processing · string · optionnel · fast | bulk
    Optional. Implies Laya if model is omitted; has no effect with explicit Jev. Omit for automatic fast/bulk selection based on item × dimension decisions.
  • share_data · boolean · optionnel
    Synchronous classification request text, labels, instructions and model results are retained for model training and operator review in private Cloudflare storage by default. Shared requests receive double per-minute and daily classification quotas. Set share_data: false or X-Classifier-Share-Data: false to opt out and use standard limits. Share only data you have permission to contribute; do not include confidential or personal information. Redaction is best effort. Billing, spending caps and input-size limits still apply.
  • instructions · string · optionnel
    Optional extra criteria, e.g. "judge only the service, ignore the food".

  Exemple d'appel

  {"name": "classify_dimensions", "arguments": {"dimensions": {}}}

  Exemple de retour

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

• classify_multi_label≈ 904 tokens

  Like classify_texts, but each text gets every label that applies (possibly none), with an independent 0-1 score per label. Use this for tagging — topics of an article, components touched by a ticket — where one answer is not enough. Set max_labels to cap how many come back per text. Labels scoring >= 0.7 are kept.

  Paramètres, retour & exemple (9)

  Paramètres

  • url · string · optionnel
    Scrape one public URL instead of inputs/items. Requires funded workspace access. Context.dev costs $0.0022 per billed attempt plus classification; long articles need Fast. Errors disclose retained charges. No automatic scrape retries.
  • model · string · optionnel · jev | laya | kev | chunklaya
  • inputs · array · optionnel
    1 to 1,000 texts to classify. Results come back in the same order.
  • labels · array · requis
    2 to 100 category names. Descriptive names classify better: "urgent bug" beats "p0". Add a label like "none of these" when none-of-the-above is a real outcome.
  • include · array · optionnel
    With url: return article.markdown and/or article.html at no extra scrape cost. Omit for compact output.
  • max_labels · integer · optionnel
    At most this many labels per text, most likely first.
  • processing · string · optionnel · fast | bulk
    Optional. Implies Laya if model is omitted; has no effect with explicit Jev. Omit to select fast for up to four labels on one text, or bulk for larger work automatically.
  • share_data · boolean · optionnel
    Synchronous classification request text, labels, instructions and model results are retained for model training and operator review in private Cloudflare storage by default. Shared requests receive double per-minute and daily classification quotas. Set share_data: false or X-Classifier-Share-Data: false to opt out and use standard limits. Share only data you have permission to contribute; do not include confidential or personal information. Redaction is best effort. Billing, spending caps and input-size limits still apply.
  • instructions · string · optionnel
    Optional extra criteria, e.g. "judge only the service, ignore the food".

  Exemple d'appel

  {"name": "classify_multi_label", "arguments": {"labels": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"usage": {}, "results": []}}

• classify_texts≈ 1300 tokens

  Sort up to 1,000 texts into exactly one of your own labels each, with confidence per answer. Use this when you have many items to triage, route, filter or bucket and do not want to read them all: search results before opening them, tickets, log lines, changed files, feedback. Do not use it for fewer than about five items you can already see — just decide. For default Jev, confidence is calibrated (answers >= 0.9 are right ~82-92% of the time; < 0.5 about 30-60%); these measurements do not apply to experimental Laya. so act on the sure ones and look at the rest yourself, or pass tier "smart" to have the unsure ones re-asked of a reasoning model.

  Paramètres, retour & exemple (9)

  Paramètres

  • url · string · optionnel
    Scrape one public URL instead of inputs/items. Requires funded workspace access. Context.dev costs $0.0022 per billed attempt plus classification; long articles need Fast. Errors disclose retained charges. No automatic scrape retries.
  • tier · string · optionnel · fast | smart
    fast (default) or smart, which re-asks answers under 0.7 confidence of a reasoning model (slower, single-label only). Independent of the Laya processing lane.
  • model · string · optionnel · jev | laya | kev | chunklaya
    Jev is default. Default/explicit jev inputs over 32,000 characters use paid Fast-only long context: up to 250,000 original cl100k_base context tokens total, 20 documents, 32 decisions and a 1 MB body. Requires paid workspace balance or active paid subscription, not signup credit. $0.084/M original context tokens counted once across inputs, independent of dimensions. Final Jev uses selected evidence; eligible chunks may be omitted, disclosed in usage.long_context. No evidence returns 422 long_context_no_evidence without charge. Explicit 'chunklaya' retains legacy opt-in (4,000,000 characters/input, 20 inputs, subject to body limit). 'laya' (512-token context) and 'kev' (8K context) remain experimental alternatives.
  • inputs · array · optionnel
    1 to 1,000 texts to classify. Results come back in the same order.
  • labels · array · requis
    2 to 100 category names. Descriptive names classify better: "urgent bug" beats "p0". Add a label like "none of these" when none-of-the-above is a real outcome.
  • include · array · optionnel
    With url: return article.markdown and/or article.html at no extra scrape cost. Omit for compact output.
  • processing · string · optionnel · fast | bulk
    Optional. Implies Laya if model is omitted; has no effect with explicit Jev. With Laya, omit to select fast for one decision or bulk for batches automatically. Explicit fast accepts one decision. Shared capacity limits can return 429.
  • share_data · boolean · optionnel
    Synchronous classification request text, labels, instructions and model results are retained for model training and operator review in private Cloudflare storage by default. Shared requests receive double per-minute and daily classification quotas. Set share_data: false or X-Classifier-Share-Data: false to opt out and use standard limits. Share only data you have permission to contribute; do not include confidential or personal information. Redaction is best effort. Billing, spending caps and input-size limits still apply.
  • instructions · string · optionnel
    Optional extra criteria, e.g. "judge only the service, ignore the food".

  Exemple d'appel

  {"name": "classify_texts", "arguments": {"labels": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"tier": "texte", "model": "texte", "usage": {}, "results": []}}

• count_labels≈ 618 tokens

  Classify up to 1,000 texts and return only a histogram: how many landed on each label, and how many the model was unsure about. Use this when you want the shape of a corpus — what share of feedback is bugs vs praise, how many search results are relevant — without pulling a thousand individual answers into context. Use classify_texts when you need the answer per item.

  Paramètres, retour & exemple (5)

  Paramètres

  • inputs · array · requis
    1 to 1,000 texts to classify. Results come back in the same order.
  • labels · array · requis
    2 to 100 category names. Descriptive names classify better: "urgent bug" beats "p0". Add a label like "none of these" when none-of-the-above is a real outcome.
  • share_data · boolean · optionnel
    Synchronous classification request text, labels, instructions and model results are retained for model training and operator review in private Cloudflare storage by default. Shared requests receive double per-minute and daily classification quotas. Set share_data: false or X-Classifier-Share-Data: false to opt out and use standard limits. Share only data you have permission to contribute; do not include confidential or personal information. Redaction is best effort. Billing, spending caps and input-size limits still apply.
  • instructions · string · optionnel
    Optional extra criteria, e.g. "judge only the service, ignore the food".
  • unsure_below · number · optionnel
    Answers with confidence under this count as unsure.

  Exemple d'appel

  {"name": "count_labels", "arguments": {"inputs": [], "labels": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"total": 1, "counts": {}, "unsure": 1, "unsure_below": 1}}

• review_uncertain≈ 662 tokens

  Classify up to 1,000 texts and return only the ones whose confidence fell under a threshold (default 0.7), each with its two most likely labels. Use this after a bulk classification to decide which items deserve your own attention: the confident answers can be trusted, these are the ones to read. Returns the index of each item so you can map back to your list.

  Paramètres, retour & exemple (5)

  Paramètres

  • below · number · optionnel
    Return items with confidence under this.
  • inputs · array · requis
    1 to 1,000 texts to classify. Results come back in the same order.
  • labels · array · requis
    2 to 100 category names. Descriptive names classify better: "urgent bug" beats "p0". Add a label like "none of these" when none-of-the-above is a real outcome.
  • share_data · boolean · optionnel
    Synchronous classification request text, labels, instructions and model results are retained for model training and operator review in private Cloudflare storage by default. Shared requests receive double per-minute and daily classification quotas. Set share_data: false or X-Classifier-Share-Data: false to opt out and use standard limits. Share only data you have permission to contribute; do not include confidential or personal information. Redaction is best effort. Billing, spending caps and input-size limits still apply.
  • instructions · string · optionnel
    Optional extra criteria, e.g. "judge only the service, ignore the food".

  Exemple d'appel

  {"name": "review_uncertain", "arguments": {"inputs": [], "labels": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"below": 1, "total": 1, "uncertain": []}}

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://classifier.dev/mcp