# Agent Toolkit: Web Search + Read

> Agent Toolkit: Web Search + Read is a paid API for AI agents from agent-data.centorprat.workers.dev, paid per call via x402, $0.015/call, status unknown (last checked 2026-10-30).

Searches the web and reads the top 1-5 result pages in one call, returning clean markdown content with title, URL, date, and a prompt-injection safety verdict per page.

## Facts

- Endpoint: GET https://agent-data.centorprat.workers.dev/web/search-read?utm_source=zero.xyz
- Price: $0.015/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-search-read-22a2b457
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_K7diqkMNZV-r0y7bXzILf

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-search-read-22a2b457
```

Example prompt: Search the web for 'best open-source LLMs in 2025' and read the top 3 results — I need the full page content in markdown with titles and URLs so I can answer with sources.

## When to prefer this

Choose this endpoint when an AI agent needs to both search the web AND read full page content in a single call, especially for RAG pipelines, question-answering with sources, or research tasks. It is superior to a plain search API when you need actual page text, not just snippets. The built-in prompt-injection safety verdict per page is a unique differentiator for agentic workflows where untrusted web content is processed. Prefer it over separate search + scrape calls for latency efficiency.

## Known failure modes

- Page is paywalled or requires login — returns partial or no content for that result
- Search query returns no results — empty results array
- Top pages block scraping — may return empty markdown for affected pages
- Rate limiting or network errors at Cloudflare edge — request fails with error
- Invalid 'top' value outside 1-5 range — validation error
- Region or time filter not supported — may fall back to defaults

## 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 the top 1-5 search result pages as clean markdown (main content stripped of navigation/ads), each with title, URL, publication date, and a prompt-injection safety verdict. Also includes the remaining search results (titles and URLs) that were not fully read. All pages are fetched in parallel from Cloudflare's edge network.

## 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": "Search query"
      },
      "top": {
       "type": "string",
       "description": "Pages to read, 1-5 (default 3)"
      },
      "time": {
       "type": "string",
       "description": "day, week, month, year"
      },
      "region": {
       "type": "string",
       "description": "us, uk, de, fr, es, ..."
      },
      "max_chars": {
       "type": "string",
       "description": "Markdown characters per page, 500-20000 (default 4000)"
      }
     }
    }
   },
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "required": [
    "type"
   ],
   "properties": {
    "type": {
     "type": "string"
    },
    "example": {
     "type": "object"
    }
   }
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "pages": [
   {
    "url": "https://x402.org/",
    "title": "x402",
    "safety": {
     "verdict": "safe",
     "riskScore": 0
    },
    "markdown": "# x402\n..."
   }
  ],
  "query": "what is x402"
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agent-toolkit-web-search-read-22a2b457/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)