
JarvisClaw — AI Gateway & API Marketplace MCP server
online · 100% uptimeio.github.api-jarvisclaw/jarvisclaw·v1.1.0320 AI models + 2,720 pay-per-call APIs. x402 USDC on Base or Solana, no API key.
0 stars47 downloads/wk
Reviews
Write oneNobody has reviewed JarvisClaw — AI Gateway & API Marketplace yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
JarvisClaw — AI Gateway & API Marketplace tools (9, 2 write)
write = sends, deletes, buys or postsaip_estimate_costFreePreview 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.
aip_execute_with_budgetwrite actionFreeRun 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.
aip_list_intentsFreeBrowse 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.
aip_resolveFreeFind 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.
chatwrite actionFreeSend 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.
discover_agentsFreeFind 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.
get_api_detailFreeGet 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.
list_modelsFreeList 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.
search_apisFreeSearch 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.
Public scan report
scanner v0.1.10 · 2026-11-03 · same rubric, same numbers if you re-run it
- Code scan3 source files scanned25/25
- Live reliabilityremote reachable in 581ms20/20
- Tool poisoning9 tool descriptions checked15/15
- Auth qualityopen endpoint exposes 2 write-action tools with no auth3/15
- Maintenancelast push 66 days ago12/15
- Maintainer identityregistry namespace matches repository owner6/10
Findings (1)
- highWrite-action tools reachable without authentication
auth.open-write
How JarvisClaw — AI Gateway & API Marketplace compares
Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 81/100
- higher than 62% of 48,255 servers
- Tools
- 9
- the typical server has 7
- Tools that change things
- 22%
- typical: 0%. Fewer write tools means less an agent can break
- Uptime
- 100%
- of our recent checks; the typical remote server answers 100%
- Response time
- 125 ms
- faster than 78% of 30,031 servers
- Downloads a week
- 47
- more than 39% of 12,191 servers with a package
What its tools let an agent do: 7 read · 2 change
Install JarvisClaw — AI Gateway & API Marketplace in Claude Code, Cursor or VS Code
claude mcp add --transport http jarvisclaw https://api.jarvisclaw.ai/mcp
What the publisher says
From the JarvisClaw — AI Gateway & API Marketplace repository's README, as published. We do not edit it. Read it on GitHub
JarvisClaw MCP Server
<!-- mcp-name: io.github.api-jarvisclaw/jarvisclaw -->
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:
OpenAI-compatible chat tool, or auto to let the router pick.
- Models — 283 of them (GPT-5, Claude Opus 5, Gemini 3, DeepSeek) behind one
(search, blockchain, code, DNS, image, document, OCR, email, geo, TTS…), of which 411 are curated. Search it, read the price, then call it.
- API marketplace — 2,720 individually priced endpoints across 40 categories
image_generation, translation…) and AIP resolves it to a provider, so the caller never has to know the URL layout.
- AIP intents — 13 intent types. Say what you need (web_search,
Counts move as the catalogue changes; listmodels, searchapis and aiplistintents are the live answer.
Quick start
Local wallet signing (recommended for x402)
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.
JARVISCLAW_WALLET_KEY=0xyourkey npx jarvisclaw-mcpClaude Desktop / Cursor, Base wallet:
{
"mcpServers": {
"jarvisclaw": {
"command": "npx",
"args": ["-y", "jarvisclaw-mcp"],
"env": {
"JARVISCLAW_WALLET_KEY": "0xYOUR_BASE_PRIVATE_KEY",
"JARVISCLAW_CHAIN": "base"
}
}
}
}Solana wallet:
{
"mcpServers": {
"jarvisclaw": {
"command": "npx",
"args": ["-y", "jarvisclaw-mcp"],
"env": {
"JARVISCLAW_WALLET_KEY": "YOUR_SOLANA_BS58_SECRET_KEY",
"JARVISCLAW_CHAIN": "solana"
}
}
}
}Direct URL (no local process)
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.
{
"mcpServers": {
"jarvisclaw": {
"type": "url",
"url": "https://api.jarvisclaw.ai/mcp",
"headers": { "Authorization": "Bearer sk-your-api-key" }
}
}
}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.
Environment variables
Tools
Shortened. The full README is on GitHub.
Nothing above is checked by us. What we check is on the safety report.
JarvisClaw — AI Gateway & API Marketplace: common questions
- Is JarvisClaw — AI Gateway & API Marketplace MCP server safe?
- Mostly: it is graded B (81/100). Read the JarvisClaw — AI Gateway & API Marketplace safety report
- How do I install JarvisClaw — AI Gateway & API Marketplace?
- It runs remotely at api.jarvisclaw.ai. Add it to Claude Code, Cursor, VS Code or Claude Desktop with the snippets above, or call it through the mcp.market gateway without installing anything.
- Does JarvisClaw — AI Gateway & API Marketplace need an API key?
- Not as far as the registry entry and our scan can tell: no credentials are declared or required.
- Is JarvisClaw — AI Gateway & API Marketplace maintained?
- The last commit was 67 days ago (2026-08-29). The latest release is v1.1.0.
- Is JarvisClaw — AI Gateway & API Marketplace up?
- 100% of our last 28 checks got an answer. We check remote servers about four times a day.
- How does JarvisClaw — AI Gateway & API Marketplace compare with other MCP servers?
- safety score 81/100 (higher than 62% of 48,255 servers); tools 9 (the typical server has 7); tools that change things 22% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.