Grounded research brief. POST { query, urls? }. Gathers sources (Wikipedia + any URLs you supply), then synthesizes a factual, cited brief: a 2-4 sentence summary, key facts, and the source list. Grounded only in the fetched sources (no free-form invention). For agent research, due diligence, and topic primers.
/api/ai/researchPAYMENT-SIGNATURE.The research API is a pay-per-call ai endpoint built for AI agents and autonomous software. Grounded research brief.
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 research data source for an agent tool-use loop, an MCP host, or a backend that needs ai data on demand without onboarding to yet another vendor portal.
| Name | Type | Description |
|---|---|---|
queryrequired | string | Topic, entity, or question to research. min 2 chars · max 400 chars |
urls | array | Optional source URLs to ground the brief in, alongside Wikipedia. |
# 1. Probe the endpoint with no auth — receive 402 with PaymentRequirements
curl -sS -X POST 'https://2s.io/api/ai/research' \
-H 'Content-Type: application/json' \
-d '{"query":"xx","urls":["https://example.com"]}'
# 2. Sign the EIP-3009 transferWithAuthorization for the advertised price +
# payTo from the 402 envelope, then retry with PAYMENT-SIGNATURE:
curl -sS -X POST 'https://2s.io/api/ai/research' \
-H 'Content-Type: application/json' \
-H 'PAYMENT-SIGNATURE: <base64-json-payload>' \
-d '{"query":"xx","urls":["https://example.com"]}'
# Or just use the canonical runner — it handles the whole loop:
# EVM_PRIVATE_KEY=0x... node --env-file=.env.local \
# --experimental-strip-types scripts/x402-pay.ts \
# 'https://2s.io/api/ai/research'import { TwoS } from '@2sio/sdk'
const client = new TwoS({
privateKey: process.env.EVM_PRIVATE_KEY as `0x${string}`,
})
const result = await client.ai.research({
"query": "xx",
"urls": [
"https://example.com"
]
})
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.ai.research(query="xx", urls=["https://example.com"])
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": "ai.research",
"arguments": {
"query": "xx",
"urls": [
"https://example.com"
]
}
}
}| Field | Type | Description |
|---|---|---|
ok | boolean | one of: true |
items | array | |
total | integer | Total matching rows upstream; null when unknown. |
source | object |
{
"ok": true,
"items": [
{
"query": "example",
"summary": "example",
"keyFacts": [
"example"
],
"sources": [
{
"title": "example",
"url": "example"
}
]
}
],
"total": 1,
"source": {
"provider": "example",
"url": "example",
"license": "example"
}
}