API Tools

jarvisclaw.ai

Provides access to AI models and APIs, including model listing, chat completions, and API discovery.

x402 supported1 endpoint9 known toolsFirst detected July 6, 2026Last detected August 19, 2026

ENDPOINT 1

https://api.jarvisclaw.ai/mcp

No auth detected

MCP server metadata

Name: jarvisclaw-mcp
Version: 1.0.0

Capabilities

resourcestools.listChanged

Server instructions

JarvisClaw is an AI API gateway supporting GPT, Claude, Gemini, DeepSeek, and more. Authentication: pass either 'Authorization: Bearer sk-...' (API key) or 'PAYMENT-SIGNATURE' (x402 USDC payment) in HTTP headers. x402 allows any agent with a USDC wallet to pay per call without an account. Use 'list_models' to see available models. Use 'chat' to call any model (OpenAI-compatible). Use 'search_apis' to find any API on the platform (thousands of catalogue endpoints plus user-published APIs); each result carries its invocation path and price. Use 'aip_resolve' to discover providers for an intent (chat, image, video, tts, search). Use 'aip_execute_with_budget' for budget-controlled AI task execution with automatic risk management. Read the 'jarvisclaw://aip-protocol' resource for full AIP documentation.

Known 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.

Inferred read-only

chat

Send a chat completion to any model on JarvisClaw through one OpenAI-compatible endpoint — GPT, Claude, Gemini, DeepSeek, and more.

Potential side effects

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.

Inferred read-only

get_api_detail

Get the full spec for any API returned by search_apis — pricing, method, and the exact request to send.

Potential side effects

discover_agents

Find other AI agents registered on JarvisClaw and connect to them directly.

Inferred read-only

aip_resolve

Find the best AI provider for a task and get ranked, priced options before you commit a cent.

Inferred read-only

aip_execute_with_budget

Run an AI task end-to-end with a hard spending cap you set.

Inferred read-only

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.

Inferred read-only

aip_estimate_cost

Preview what a task will cost before committing — get an estimated price for an intent without running it or spending anything.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.jarvisclaw-mcp]
url = "https://api.jarvisclaw.ai/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "jarvisclaw-mcp": {
      "type": "http",
      "url": "https://api.jarvisclaw.ai/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: jarvisclaw-mcp
Remote MCP URL: https://api.jarvisclaw.ai/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "jarvisclaw-mcp": {
      "url": "https://api.jarvisclaw.ai/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "jarvisclaw-mcp": {
      "type": "http",
      "url": "https://api.jarvisclaw.ai/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "jarvisclaw-mcp",
  "transport": "streamable-http",
  "url": "https://api.jarvisclaw.ai/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Loading Trust v2 evidence…

Checking the associated registrable domain. The BuiltWith key remains server-side.

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.