{"uid":"cap_xpUpsD9tUeWpA3P4CAYKZ","slug":"web-search-read-top-pages-ddb2187e","name":"Web Search + Read Top Pages","description":"Search and contents in one call (Exa search + contents, Firecrawl search with markdown, cheaper): authority-ranked Google-quality results, then the top 1-5 pages read as clean markdown (main content only) with title, author, date and a prompt-injection safety verdict per page, plus the other results. Everything an agent needs to answer with sources.","url":"https://agent-search.centorprat.workers.dev/search-read?utm_source=zero.xyz","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"time":{"type":"string","description":"freshness: hour, day, week, month or year (optional)"},"query":{"type":"string","description":"What to search for"},"country":{"type":"string","description":"2-letter country the results are for: us, gb, de, es, fr, in, br, ... (default us)"},"private":{"type":"boolean","description":"true = the query is not logged or cached (default false)"},"category":{"type":"string","description":"optional category, as in /search"},"numPages":{"type":"integer","description":"pages to read, 1-5 (default 3)"},"maxCharacters":{"type":"integer","description":"markdown characters per page, 500-20000 (default 4000)"},"excludeDomains":{"type":"array","items":{"type":"string"},"description":"never these domains"},"includeDomains":{"type":"array","items":{"type":"string"},"description":"only these domains"}}},"responseSchema":{"type":"json","example":{"pages":[{"url":"https://x402.org/","title":"x402","safety":{"verdict":"safe"},"markdown":"# x402 ..."}],"query":"...","otherResults":[]}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.015","displayCostAsset":"USDC","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"probe","requiresHandshake":false,"reviewCount":0,"rating":{"score":"0.00","successRate":"0.00","reviews":0,"stars":null,"state":"unrated"},"availabilityStatus":"unknown","priceObserved":null,"sessionDeposit":null,"pricing":{"kind":"static","summary":"$0.015/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.015","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.015","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_AYMlvza3GpoHb0cRRGKiY","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.015","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Performs a web search and returns the top 1-5 pages as clean markdown with title, author, date, and a prompt-injection safety verdict, plus remaining search results.","exampleAgentPrompt":"Search for 'best practices for AI agent memory management' and read the top 3 pages — give me clean markdown with sources, authors, and dates, and flag anything that looks like prompt injection.","exampleUseCases":[{"title":"Fact-checking a breaking news claim","prompt":"Search for 'WHO mpox emergency declaration 2025' and read the top 4 results from the past week — I need the full page content with dates and authors so I can verify what's actually been announced."},{"title":"Competitive research with full content","prompt":"Search for 'Stripe vs Brex corporate cards comparison' and pull the top 3 pages as markdown — I want the actual article text, not just snippets, so I can compare their features in detail."},{"title":"Technical documentation lookup","prompt":"Search for 'Next.js 15 server actions tutorial' and read the top 2 pages, limiting each to 6000 characters — I need the full code examples and explanations from the actual pages."}],"resultDescription":"Returns a JSON object with a 'pages' array (each entry has url, title, safety verdict, and markdown content of the page), the original query string, and an 'otherResults' array of additional search results that were not fully read. Each page's safety verdict indicates whether prompt-injection risks were detected in the page content.","failureModes":["Query returns no results — empty pages array and otherResults","Target page blocks scraping — page may be missing or have empty markdown","numPages out of range (must be 1-5) — validation error","Invalid country code — may fall back to default or return error","Page content exceeds maxCharacters and is truncated","Network timeout on slow or large pages","Safety verdict flags a page as unsafe due to detected injection attempts"],"whenToPreferThis":"Choose this endpoint when you need both search results AND the actual page content in a single API call, avoiding the need to chain a search call with separate scrape calls. Ideal for research tasks, Q&A with sources, fact-checking, and content summarization where you need authoritative text and not just URLs. Prefer over plain search endpoints when the agent needs to read and cite specific content. Prefer over standalone scrapers when you don't yet know which URL to read. The built-in prompt-injection safety verdict makes it safer for agentic pipelines that process untrusted web content.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-30T12:32:37.014Z","isFirstParty":false,"canonicalSlug":"web-search-read-top-pages-ddb2187e"}