# agentsvc.io Search-Read (Web & News Search with Full-Page Content)

> agentsvc.io Search-Read (Web & News Search with Full-Page Content) is a paid API for AI agents from agentsvc.io, paid per call via x402, $0.005/call, status unknown (last checked 2026-10-10).

Performs a web or news search for a query and returns ranked results with full markdown content, snippets, and an optional AI-generated summary answer.

## Facts

- Endpoint: POST https://agentsvc.io/api/v1/proxy/search-read?utm_source=zero.xyz
- Price: $0.005/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-10
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agentsvc-io-search-read-web-news-search-with-full-page-content-b5faf934
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_ywXcD_NkeaR_thcxINK5d

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 agentsvc-io-search-read-web-news-search-with-full-page-content-b5faf934 -d '<json body>'
```

Example prompt: Search the web for 'open source LLM benchmarks 2025' and give me the top 3 results with full content so I can read what each page actually says.

## When to prefer this

Choose this endpoint when you need both search result metadata AND the full readable content of each result page in a single call — ideal for research tasks where you want to read what pages actually say, not just their titles and snippets. Prefer this over a bare search API when markdown body content is needed for downstream reasoning. Prefer over a raw scrape endpoint when you need ranked discovery of relevant URLs rather than fetching a known URL. The news source option makes it suitable for time-sensitive queries about current events.

## Known failure modes

- Query returns zero results if search engine finds no matches
- Individual result pages may fail to fetch (ok: false) while others succeed
- max_chars limit may truncate long pages, cutting off content mid-sentence
- News source may have no recent articles matching the query
- Rate limits or payment failures return HTTP 402 or 429 errors
- Summary answer field may be null if no direct answer is extractable

## How this service works

86 APIs for AI agents: web scraping and crawling to Markdown, AI summaries, data extraction and cited answers, screenshots and PDF, PDF, OCR and document conversion, news, paper and developer search and more, paid per call with USDC on Base, Solana, Polygon or Arbitrum via x402. No account, no API key, free sample on every service.

## Output

Returns a JSON object with a list of ranked search results, each containing the URL, title, snippet, full markdown body text, and word count. Also includes a summary object with an optional direct answer, a heading, and an abstract. Metadata includes the number of successful results and the fetch timestamp.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "count": {
   "type": "integer",
   "default": 3,
   "maximum": 5,
   "minimum": 1
  },
  "query": {
   "type": "string"
  },
  "source": {
   "enum": [
    "web",
    "news"
   ],
   "type": "string",
   "default": "web"
  },
  "max_chars": {
   "type": "integer",
   "default": 4000,
   "maximum": 20000,
   "minimum": 500
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "data": {
   "query": "x402 payment protocol",
   "source": "web",
   "results": [
    {
     "ok": true,
     "url": "https://en.wikipedia.org/wiki/The_Graph",
     "rank": 1,
     "title": "The Graph - Wikipedia",
     "snippet": " a platform designed to manage payments and policies for autonomous AI agents. It's built on Coinbase’s x402 protocol and Google’s agent-to-agent (A2A)",
     "markdown": "[Jump to content](#bodyContent)\n\nFrom Wikipedia, the free encyclopedia\n\n![](//thumb.wikimedia.org/wikipedia/en/thumb/b/b4/Ambox_important.svg/40px-Ambox_impo…",
     "word_count": 38
    }
   ],
   "summary": {
    "answer": null,
    "heading": "The Graph",
    "abstract": "The Graph is an open-source, decentralized protocol that powers the indexing and querying of blockchain data. It enables developers to build scalable web3 de…"
   },
   "ok_count": 1,
   "fetched_at": "2026-10-06T14:29:39.582Z"
  },
  "success": true
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agentsvc-io-search-read-web-news-search-with-full-page-content-b5faf934/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agentsvc.io](https://www.zero.xyz/host/agentsvc.io/llms.txt)