JarvisClaw — AI Gateway & API Marketplace

Measured conclusion: Deep-tested. L2 outcome: tools_ok.

320 AI models + 2,720 pay-per-call APIs. x402 USDC on Base or Solana, no API key.

Add to your agent

Copy this into your MCP client config:

{
  "mcpServers": {
    "JarvisClaw — AI Gateway & API Marketplace": {
      "url": "https://api.jarvisclaw.ai/mcp",
      "transport": "streamable-http"
    }
  }
}

Measured tools (9)

• list_models

  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.

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• chat

  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.

  Parameters:

  • model (required) — string — 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 (required) — array — Chat messages array.
  • max_tokens — integer — Maximum tokens to generate. Optional.
  • temperature — number — Sampling temperature (0-2). Optional.

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• search_apis

  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.

  Parameters:

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

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• get_api_detail

  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.

  Parameters:

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

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• discover_agents

  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.

  Parameters:

  • tags — string — Comma-separated tags to filter by.
  • search — string — Search query (matches agent name and description).
  • category — string — Filter by category.

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• aip_resolve

  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.

  Parameters:

  • intent (required) — string — The intent type (e.g. chat_completion, image_generation)
  • features — array — Required features (e.g. streaming, function_calling, vision)
  • optimize_for — string — Optimization preference: cost, quality, or latency
  • max_price_usd — number — Maximum acceptable price per request in USD (optional filter)

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• aip_execute_with_budget

  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.

  Parameters:

  • intent (required) — string — The intent type
  • payload (required) — object — The actual request payload (e.g. {model, messages} for chat, {prompt, size} for images)
  • max_total_usd — number — Maximum budget for this request in USD (hard cap)
  • preferred_payment — string — Payment method preference

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• aip_list_intents

  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.

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• aip_estimate_cost

  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.

  Parameters:

  • intent (required) — string — The intent type
  • optimize_for — string

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

Publisher website Repository

Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.