AI web search optimized for agents. Returns ranked results with the relevant extracted content of each page (not just a link + blurb), plus a relevance score. topic=news for recent reporting. Distinct from search.web (raw SERP) — this returns clean, LLM-ready page content per result.
/api/search/aiPAYMENT-SIGNATURE.The ai API is a pay-per-call search endpoint built for AI agents and autonomous software. AI web search optimized for agents.
There is no signup and no API key. An agent (or any HTTP client) hits the endpoint, receives an x402 "402 Payment Required" challenge, signs a sub-cent USDC payment on Base or Solana, and retries — the data comes back on the paid request. That makes it a drop-in ai data source for an agent tool-use loop, an MCP host, or a backend that needs search data on demand without onboarding to yet another vendor portal.
| Name | Type | Description |
|---|---|---|
qrequired | string | Search query. min 2 chars · max 400 chars |
maxResults | integer | min 1 · max 10 |
topic | string | one of: general | news |
# 1. Probe with no auth → 402 envelope with PaymentRequirements curl -sS 'https://2s.io/api/search/ai?q=xx&maxResults=1&topic=general' # 2. Sign + retry with PAYMENT-SIGNATURE: curl -sS 'https://2s.io/api/search/ai?q=xx&maxResults=1&topic=general' \ -H 'PAYMENT-SIGNATURE: <base64-json-payload>' # Or use the canonical runner (handles probe → sign → retry): # EVM_PRIVATE_KEY=0x... node --env-file=.env.local \ # --experimental-strip-types scripts/x402-pay.ts \ # 'https://2s.io/api/search/ai?q=xx&maxResults=1&topic=general'
import { TwoS } from '@2sio/sdk'
const client = new TwoS({
privateKey: process.env.EVM_PRIVATE_KEY as `0x${string}`,
})
const result = await client.search.ai({
"q": "xx",
"maxResults": 1,
"topic": "general"
})
console.log('endpoint:', result.endpoint)
console.log('cost:', result.costUsd, 'USDC')
console.log('tx:', result.settlement?.txHash)
console.log('data:', result.data)import os
from twosio import TwoS
client = TwoS(private_key=os.environ["EVM_PRIVATE_KEY"])
result = client.search.ai(q="xx", maxResults=1, topic="general")
print("endpoint:", result.endpoint)
print("cost:", result.cost_usd, "USDC")
print("tx:", (result.settlement or {}).get("tx_hash"))
print("data:", result.data)// 1. Add @2sio/mcp to your MCP host config (Claude Desktop example below).
// EVM_PRIVATE_KEY funds x402 payments per call.
// claude_desktop_config.json
{
"mcpServers": {
"2sio": {
"command": "npx",
"args": ["-y", "@2sio/mcp"],
"env": { "EVM_PRIVATE_KEY": "0x..." }
}
}
}
// 2. Once the server is running, agents call this tool via standard MCP:
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "search.ai",
"arguments": {
"q": "xx",
"maxResults": 1,
"topic": "general"
}
}
}| Field | Type | Description |
|---|---|---|
ok | boolean | one of: true |
items | array | |
total | integer | Total matching rows upstream; null when unknown. |
source | object |
{
"ok": true,
"items": [
{
"title": "example",
"url": "example",
"content": "example",
"score": 1
}
],
"total": 1,
"source": {
"provider": "example",
"url": "example",
"license": "example"
}
}