# ScrapeGraphAI Search

> ScrapeGraphAI Search is a paid API for AI agents from ScrapeGraphAI at mpp.orthogonal.com, paid per call via MPP, $0.03/call, status unknown (last checked 2026-10-10).

Runs a web search, scrapes the top N result URLs, and optionally applies LLM extraction with a prompt and schema to return structured data.

## Facts

- Endpoint: POST https://mpp.orthogonal.com/scrapegraphai/api/search?utm_source=zero.xyz
- Price: $0.03/call
- Payment: MPP
- Status: unknown
- Last checked: 2026-10-10
- Activations on Zero: 0
- Provider: ScrapeGraphAI
- Docs: https://v2-api.scrapegraphai.com
- Website: https://v2-api.scrapegraphai.com
- Tags: scraping, extraction, llm, crawl, web, data
- Canonical page: https://www.zero.xyz/c/scrapegraphai-search-f8cd6b4c
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_3w64HEb5KncoxrwODkIzz

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 scrapegraphai-search-f8cd6b4c -d '<json body>'
```

Example prompt: Search for 'best electric SUVs 2025', scrape the top 5 results, and extract the car name, price range, and range in miles from each page as structured JSON.

## When to prefer this

Choose this endpoint when you need to both search the web AND extract structured data from the results in a single call — ideal for research automation, competitive intelligence, or any workflow where you want LLM-parsed fields from live search results without chaining separate search and scrape calls. Prefer it over a standalone scrape endpoint when you don't already know the target URLs.

## Known failure modes

- Search query returns no results — empty results array returned
- Target URLs block scraping (bot detection, paywalls) — partial or empty content for affected URLs
- LLM extraction prompt is ambiguous or schema doesn't match page content — extraction returns nulls or partial fields
- N is too large — rate limiting or timeout on scraping many pages
- Invalid JSON schema provided — extraction step fails with schema validation error

## How this service works

Runs a search, scrapes the top N result URLs, optionally runs LLM extraction with prompt and schema.

## Output

Returns scraped content from the top N search result URLs, plus optionally LLM-extracted structured data matching the provided prompt and JSON schema — giving the agent both raw page content and parsed fields in one call.

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/scrapegraphai-search-f8cd6b4c/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from mpp.orthogonal.com](https://www.zero.xyz/host/mpp.orthogonal.com/llms.txt)