io.github.api-jarvisclaw/jarvisclaw

Est-ce que io.github.api-jarvisclaw/jarvisclaw est sûr ?

Au dernier audit MCP Hub, le serveur MCP « io.github.api-jarvisclaw/jarvisclaw » 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

• aip_estimate_cost≈ 148 tokens

  Preview what a task will cost before committing — get an estimated price for an intent without running it or spending anything. Ideal for budget planning and comparing options up front. Free.

  Paramètres, retour & exemple (2)

  Paramètres

  • intent · string · requis · chat_completion | image_generation | video_generation | text_to_speech | web_search | knowledge_search
    The intent type
  • optimize_for · string · optionnel · cost | quality | latency

  Exemple d'appel

  {"name": "aip_estimate_cost", "arguments": {"intent": "chat_completion"}}

  Exemple de retour

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

• aip_execute_with_budget≈ 292 tokens

  Run an AI task end-to-end with a hard spending cap you set. This is the primary AIP action: it resolves the best provider, runs a risk check, pre-deducts against your budget, executes the call, and settles on-chain via x402 — all in one step. You never overspend past max_total_usd, and settlement is automatic. Supports chat, image, video, speech, prompt optimization, web search, and knowledge search intents.

  Paramètres, retour & exemple (4)

  Paramètres

  • intent · string · requis · chat_completion | image_generation | video_generation | text_to_speech | prompt_optimization | web_search | knowledge_search
    The intent type
  • payload · object · requis
    The actual request payload (e.g. {model, messages} for chat, {prompt, size} for images)
  • max_total_usd · number · optionnel
    Maximum budget for this request in USD (hard cap)
  • preferred_payment · string · optionnel · balance | credit | crypto | auto
    Payment method preference

  Exemple d'appel

  {"name": "aip_execute_with_budget", "arguments": {"intent": "chat_completion", "payload": {}}}

  Exemple de retour

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

• aip_list_intents≈ 78 tokens

  Browse every AI task type AIP can route — chat, image, video, speech, web search, knowledge search — with a short description of each. Call this first to see what's on the menu before you resolve or execute. Free.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "aip_list_intents", "arguments": {}}

  Exemple de retour

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

• aip_resolve≈ 358 tokens

  Find the best AI provider for a task and get ranked, priced options before you commit a cent. Pass a known intent type (chat_completion, code_execution, code_generation, data_analysis, document_processing, image_generation, knowledge_search, prompt_optimization, text_to_speech, translation, utility, video_generation, web_search) for structured routing, or a plain-language query for semantic matching. Each match returns provider, model, live per-request price, and a ready-to-call endpoint. Free to call — no payment until you execute.

  Paramètres, retour & exemple (4)

  Paramètres

  • intent · string · requis · chat_completion | code_execution | code_generation | data_analysis | document_processing | image_generation | knowledge_search | prompt_optimization
    The intent type (e.g. chat_completion, image_generation)
  • features · array · optionnel
    Required features (e.g. streaming, function_calling, vision)
  • optimize_for · string · optionnel · cost | quality | latency
    Optimization preference: cost, quality, or latency
  • max_price_usd · number · optionnel
    Maximum acceptable price per request in USD (optional filter)

  Exemple d'appel

  {"name": "aip_resolve", "arguments": {"intent": "chat_completion"}}

  Exemple de retour

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

• chat≈ 250 tokens

  Send a chat completion to any model on JarvisClaw through one OpenAI-compatible endpoint — GPT, Claude, Gemini, DeepSeek, and more. Pass a specific model ID or use 'auto' for smart routing to the best fit. One tool, every frontier model, no per-provider setup.

  Paramètres, retour & exemple (4)

  Paramètres

  • model · string · requis
    Model ID from list_models (e.g. 'openai/gpt-4o-mini', 'anthropic/claude-sonnet-4.6', 'google/gemini-2.5-flash'). Use 'auto' for smart routing.
  • messages · array · requis
    Chat messages array.
  • max_tokens · integer · optionnel
    Maximum tokens to generate. Optional.
  • temperature · number · optionnel
    Sampling temperature (0-2). Optional.

  Exemple d'appel

  {"name": "chat", "arguments": {"model": "texte", "messages": []}}

  Exemple de retour

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

• discover_agents≈ 160 tokens

  Find other AI agents registered on JarvisClaw and connect to them directly. Search by capability, category, or name to get each agent's MCP URL and API endpoints — so your agent can delegate, collaborate, or chain work with others in the network.

  Paramètres, retour & exemple (3)

  Paramètres

  • tags · string · optionnel
    Comma-separated tags to filter by.
  • search · string · optionnel
    Search query (matches agent name and description).
  • category · string · optionnel · ai | defi | data | agent | tool
    Filter by category.

  Exemple d'appel

  {"name": "discover_agents", "arguments": {"tags": "texte", "search": "texte", "category": "ai"}}

  Exemple de retour

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

• get_api_detail≈ 117 tokens

  Get the full spec for any API returned by search_apis — pricing, method, and the exact request to send. Works for both a user-published API slug and a catalogue handle like 'federation/40'. Use this before wiring a call in.

  Paramètres, retour & exemple (1)

  Paramètres

  • slug · string · requis
    A user-published API slug, or a catalogue handle ('federation/40' or just '40').

  Exemple d'appel

  {"name": "get_api_detail", "arguments": {"slug": "texte"}}

  Exemple de retour

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

• list_models≈ 73 tokens

  List every AI model available on JarvisClaw — GPT, Claude, Gemini, DeepSeek, and more — with the model IDs you plug straight into the chat tool. Free, and the fastest way to see what you can call.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "list_models", "arguments": {}}

  Exemple de retour

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

• search_apis≈ 167 tokens

  Search every API on JarvisClaw — thousands of callable endpoints across search, blockchain, image, data, document and more, plus APIs other developers have published. Returns the exact invocation path and per-call price for each result, so you can call one directly afterwards. Free to search; you only pay when you invoke.

  Paramètres, retour & exemple (2)

  Paramètres

  • query · string · optionnel
    Search query (matches name, description, tags and category).
  • category · string · optionnel
    Optional category filter, e.g. 'search', 'blockchain', 'image', 'data', 'document', 'storage'.

  Exemple d'appel

  {"name": "search_apis", "arguments": {"query": "texte", "category": "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://api.jarvisclaw.ai/mcp