# Agent Toolkit Web Research

> Agent Toolkit Web Research is a paid API for AI agents from agent-data.centorprat.workers.dev, paid per call via x402, $0.05/call, status unknown (last checked 2026-10-30).

Performs a multi-source web research query by searching, reading up to 8 full pages as clean markdown with prompt-injection checks, and returning key passages with their sources.

## Facts

- Endpoint: GET https://agent-data.centorprat.workers.dev/web/research?utm_source=zero.xyz
- Price: $0.05/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-30
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agent-toolkit-web-research-86c6142c
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_J1j9oxkmFnJPwGnGY-eO-

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability agent-toolkit-web-research-86c6142c
```

Example prompt: Can you research 'best open-source LLM fine-tuning frameworks in 2024' by reading the top 8 pages and pulling the key passages with their sources?

## When to prefer this

Choose this endpoint when an agent needs evidence from multiple websites rather than a single snippet — it combines search and full-page reading in one call with source attribution and injection-safe markdown. Prefer it over single-page scrapers when breadth of evidence matters, or over basic search APIs when full page content (not just titles/snippets) is required to answer a query accurately.

## Known failure modes

- Query parameter 'q' missing — returns 400 error
- Pages are inaccessible or blocked — fewer than requested top pages returned
- No strong relevant passages found — returns minimal or empty results
- Time filter too narrow — results may be sparse or outdated
- Prompt-injection attempt detected in page content — affected page content sanitized or excluded
- Rate limiting or payment failure — 402 response requiring valid x402 payment

## How this service works

Pay-per-call data and tools for AI agents, $0.002-0.01 per call in USDC via x402 (Base, Polygon or Solana), no account or API key; MAX tiers ($0.05-0.25) run deeper jobs. Agent toolkit: web search, search + read top pages, any page as clean markdown with a prompt-injection check, which-x402-API-to-call recommender, seller check. Data: Google Maps places with contacts, YouTube video data and transcripts, job listings (Indeed, LinkedIn, 13 boards), Google Ads Transparency, TikTok comments, Pinterest, Airbnb, Redfin, AliExpress, app stores, live sports, website and SEO checks, Shopify store tech stacks, and onchain token / address risk checks.

## Output

Returns key passages extracted from up to 8 full web pages that answer the query, each passage tagged with its source URL. Content is delivered as clean markdown with prompt-injection checks applied, giving agents sourced, evidence-backed information from multiple sites in a single call.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "$schema": "https://json-schema.org/draft/2020-12/schema",
 "required": [
  "input"
 ],
 "properties": {
  "input": {
   "type": "object",
   "required": [
    "type",
    "method"
   ],
   "properties": {
    "type": {
     "type": "string",
     "const": "http"
    },
    "method": {
     "enum": [
      "GET",
      "HEAD",
      "DELETE"
     ],
     "type": "string"
    },
    "queryParams": {
     "type": "object",
     "required": [
      "q"
     ],
     "properties": {
      "q": {
       "type": "string",
       "description": "what to research"
      },
      "top": {
       "type": "string",
       "description": "pages to read, 1-8 (default 8)"
      },
      "time": {
       "type": "string",
       "description": "d | w | m | y (optional)"
      },
      "region": {
       "type": "string",
       "description": "us | uk | de | ... (default us)"
      }
     }
    }
   },
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "required": [
    "type"
   ],
   "properties": {
    "type": {
     "type": "string"
    },
    "example": {
     "type": "object"
    }
   }
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "pages": [
   {
    "url": "...",
    "title": "...",
    "markdown": "..."
   }
  ],
  "query": "...",
  "keyPassages": [
   {
    "url": "https://...",
    "text": "..."
   }
  ]
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agent-toolkit-web-research-86c6142c/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agent-data.centorprat.workers.dev](https://www.zero.xyz/host/agent-data.centorprat.workers.dev/llms.txt)