com.elopstudio.aiwave/ai-wave

Est-ce que com.elopstudio.aiwave/ai-wave est sûr ?

Au dernier audit MCP Hub, le serveur MCP « com.elopstudio.aiwave/ai-wave » 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 8 outils

• compare_models≈ 172 tokens

  Put two or more models side by side: price, context, benchmark scores per subject, and what each costs per month at a given volume. Use this instead of calling get_model repeatedly: it aligns the fields and marks which subjects a model has not been tested on, so a missing score is not read as a low one.

  Paramètres, retour & exemple (2)

  Paramètres

  • ids · array · requis
    2-6 OpenRouter ids, e.g. ['anthropic/claude-opus-5','openai/gpt-5.2']
  • monthlyMillionTokens · number · optionnel
    Volume for the cost estimate. Default 10 (10M tokens a month).

  Exemple d'appel

  {"name": "compare_models", "arguments": {"ids": []}}

  Exemple de retour

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

• estimate_cost≈ 152 tokens

  What one model costs per month at a given token volume, in USD and KRW. Token prices are per million and hard to reason about directly; this turns them into a monthly bill. Input and output are mixed 75/25 unless you pass your own split.

  Paramètres, retour & exemple (3)

  Paramètres

  • id · string · requis
    OpenRouter id or Hugging Face repo id
  • inputShare · number · optionnel
    0-1, share of tokens that are input. Default 0.75
  • monthlyMillionTokens · number · optionnel
    Default 10

  Exemple d'appel

  {"name": "estimate_cost", "arguments": {"id": "texte"}}

  Exemple de retour

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

• find_replacement≈ 141 tokens

  What to switch to when a model is gone or you need a fallback. Ranked by closeness in measured performance, not by vendor or price: what you usually need to preserve first is the quality of the output. Candidates whose context window is less than half the original are excluded. Returns the score, price and context deltas so you can judge; we do not pick for you.

  Paramètres, retour & exemple (1)

  Paramètres

  • id · string · requis
    OpenRouter id or Hugging Face repo id

  Exemple d'appel

  {"name": "find_replacement", "arguments": {"id": "texte"}}

  Exemple de retour

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

• get_model≈ 68 tokens

  Pricing, context length and catalog status for one model. Accepts an OpenRouter id (anthropic/claude-opus-5) or a Hugging Face repo id.

  Paramètres, retour & exemple (1)

  Paramètres

  • id · string · requis

  Exemple d'appel

  {"name": "get_model", "arguments": {"id": "texte"}}

  Exemple de retour

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

• get_price_history≈ 119 tokens

  Price history for one model: when the price changed and to what. The public catalog only exposes the current price, so this answers 'was this cheaper last month?'. Each entry holds until the next one. History starts when AI Wave began recording, not when the model launched.

  Paramètres, retour & exemple (1)

  Paramètres

  • id · string · requis
    OpenRouter id or Hugging Face repo id

  Exemple d'appel

  {"name": "get_price_history", "arguments": {"id": "texte"}}

  Exemple de retour

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

• get_today≈ 97 tokens

  Today in one call: the top 5 models, which ones climbed, whose pricing changed in the last 24h, and what was newly listed in the last 7 days. Use this instead of paging list_model_changes and re-deriving the summary: price changes are already collapsed to one per model, with the raw count kept.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "get_today", "arguments": {}}

  Exemple de retour

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

• list_model_changes≈ 200 tokens

  Changes across AI models: new releases, price changes, API changes and deprecations. Normalized from vendor release notes, Hugging Face, the OpenRouter catalog, GitHub and the LiteLLM price map, deduplicated per model, each marked official or pending review. Poll with `since` (unix seconds) and feed the returned `latest` back next time.

  Paramètres, retour & exemple (4)

  Paramètres

  • type · string · optionnel · new_model | price_change | api_change | open_source_surge | deprecation
  • limit · number · optionnel
    1-100, default 20
  • model · string · optionnel
    Vendor slug, e.g. claude
  • since · number · optionnel
    Unix seconds. Only changes detected after this, oldest first.

  Exemple d'appel

  {"name": "list_model_changes", "arguments": {"type": "new_model", "limit": 1, "model": "texte", "since": 1}}

  Exemple de retour

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

• search_models≈ 422 tokens

  Shortlist models by budget, context and capability, ranked by measured performance. Use this to answer 'which model should I use for X': it returns benchmark scores alongside price so the trade-off is visible in one call. Sort by a subject (math, coding, science, reading) to find a model good at one thing.

  Paramètres, retour & exemple (9)

  Paramètres

  • mode · string · optionnel · chat | embedding | rerank | audio_transcription | audio_speech | video_generation
    What the model does. Non-chat modes are priced in other units: check price.unit.
  • limit · number · optionnel
    1-50, default 10
  • sortBy · string · optionnel · intelligence | korean | buzz | science | math | coding | reading | knowledge
    Ranking basis. Default 'intelligence' (overall). 'buzz' is popularity, not skill.
  • vendor · string · optionnel
    OpenRouter namespace, e.g. anthropic
  • accepts · string · optionnel · text | image | audio | video | file
    What the model must be able to take in, e.g. image for vision tasks.
  • outputs · string · optionnel · text | image | audio | video
    What the model produces. A model that accepts video but writes text is 'text', not 'video': filter on what you need made, not what it can read.
  • minContext · number · optionnel
  • maxInputPrice · number · optionnel
    USD per 1M input tokens
  • minIntelligence · number · optionnel
    Lowest acceptable overall index. Leaders sit near 53; the median is 16.

  Exemple d'appel

  {"name": "search_models", "arguments": {"mode": "chat", "limit": 1, "sortBy": "intelligence", "vendor": "texte", "accepts": "text", "outputs": "text"}}

  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://aiwave.elopstudio.com/api/mcp