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.
Takes no parameters.

io.github.api-jarvisclawPublished by GitHub account api-jarvisclawv1.1.0Updated Oct 24, 2026
320 AI models + 2,720 pay-per-call APIs. x402 USDC on Base or Solana, no API key.
JarvisClaw is an AI gateway and pay-per-call API marketplace that lets an assistant chat with many models, search and call priced APIs, and run budget-capped AI
Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.
Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.
Read https://sourceweft.com/mcp/io.github.api-jarvisclaw%2Fjarvisclaw/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.Add this to your client's mcpServers config.
{
"mcpServers": {
"jarvisclaw-ai-gateway-api-marketplace": {
"type": "http",
"url": "https://api.jarvisclaw.ai/mcp"
}
}
}283 AI models and 2,720 pay-per-call APIs through one MCP server. Settles in USDC on Base or Solana over x402 — no account, no API key, no subscription.
Three ways to reach a service:
chat tool, or auto to let the router pick.web_search,
image_generation, translation…) and AIP resolves it to a provider, so the caller
never has to know the URL layout.Counts move as the catalogue changes; list_models, search_apis and
aip_list_intents are the live answer.
Run this package. It presents itself to your client as a normal stdio MCP server, forwards every request to the gateway, and when a call needs paying it signs the x402 payment on your machine and retries. Your private key is never transmitted — only the signed payment payload is.
Claude Desktop / Cursor, Base wallet:
Solana wallet:
For Claude Code, Cursor, or any client with Streamable HTTP transport. One less hop, but there is no wallet in this path: free tools work, and paid tools need a pre-paid API key, because nothing here can sign a payment.
Without the header the same URL still lists the catalogue for free; paid tools answer with an x402 quote that you would have to sign yourself.
Free tools answer without credentials, so you can list the catalogue before deciding to
pay for anything. Protocol methods (initialize, tools/list, resources/list) are
free too.
A paid tool called without either does not fail — it answers with an x402 quote:
With JARVISCLAW_WALLET_KEY set, all three steps happen inside this process and your
client just sees the result. Without it, the quote is passed through to your client
unanswered.
Both chains are live, which most x402 sellers cannot say: settle wherever the agent already holds USDC rather than bridging to reach one gateway. Every paid response carries an EIP-712 signed settlement receipt that a third party can verify offline — recompute the hashes, recover the signer, check the tx on-chain — without trusting us.
npm audit reports 3 moderate advisories reachable through @solana/web3.js
(itself, plus jayson and uuid). 1.98.4 is the latest release and is inside the
flagged range, so there is no version to move to; npm's suggested "fix" is a
downgrade to 0.0.3, which is not a real option. Tracked, not resolved.
This applies to Base-only users too: @solana/web3.js is a static import in the
entry module, so it loads whatever JARVISCLAW_CHAIN is set to (measured: 6 module
resolutions on the Base path). Only the signer object is constructed lazily.
MIT
Source: README.md at commit d2690f5
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.
Takes no parameters.
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.
modelrequiredmessagesrequiredmax_tokenstemperatureSearch 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.
querycategoryGet 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.
slugrequiredFind 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.
tagssearchcategoryFind 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.
intentrequiredfeaturesoptimize_formax_price_usdRun 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.
intentrequiredpayloadrequiredmax_total_usdpreferred_paymentBrowse 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.
Takes no parameters.
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.
intentrequiredoptimize_for90% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
Declare a license in the repository or the registry entry.
JARVISCLAW_WALLET_KEY=0xyourkey npx jarvisclaw-mcp{ "mcpServers": { "jarvisclaw": { "command": "npx", "args": ["-y", "jarvisclaw-mcp"], "env": { "JARVISCLAW_WALLET_KEY": "0xYOUR_BASE_PRIVATE_KEY", "JARVISCLAW_CHAIN": "base" } } }}{ "mcpServers": { "jarvisclaw": { "command": "npx", "args": ["-y", "jarvisclaw-mcp"], "env": { "JARVISCLAW_WALLET_KEY": "YOUR_SOLANA_BS58_SECRET_KEY", "JARVISCLAW_CHAIN": "solana" } } }}{ "mcpServers": { "jarvisclaw": { "type": "url", "url": "https://api.jarvisclaw.ai/mcp", "headers": { "Authorization": "Bearer sk-your-api-key" } } }}tools/call → 402 with payment terms (amount, asset, payTo, network) → this proxy signs a USDC authorization locally → retry with PAYMENT-SIGNATURE → resultnpm installnpm run build # tsc → dist/npm test # bun test — x402 signer unit tests