Hello

element?","exampleUseCases":[{"title":"Article body extraction for summarization","prompt":"Pull out the main content text from https://news.example.com/2024/top-story so I can summarize it."},{"title":"Main content from local HTML snippet","prompt":"I have some HTML I scraped earlier — can you extract just the text inside the main element from it?"},{"title":"Content quality check on a landing page","prompt":"Fetch the main section text from https://mysite.com/landing-page so I can check what content visitors actually see."}],"resultDescription":"Returns the extracted text content of the //main element found on the target page or within the provided HTML. If the page was fetched via URL, the response reflects the final resolved URL after any redirects.","failureModes":["No //main element found in the HTML — returns empty or null result","URL is unreachable or returns non-200 status — fetch error","SSRF-blocked URL (private IP range, localhost) — rejected for safety","HTML input exceeds 200,000 character limit — validation error","URL shorter than 8 characters or longer than 2048 characters — validation error","Payment of $0.005 USDC not provided — 402 Payment Required"],"whenToPreferThis":"Choose this endpoint when you specifically need the text content of the semantic

HTML element from a page, rather than a full markdown conversion or all link/href attributes. It is ideal when you want structured XPath-based extraction that is predictable and SSRF-safe, and when you have either a public URL or a raw HTML string to parse. Prefer the free sandbox POST /v1/sandbox/xpath-main first to test; use this paid endpoint for production use.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-02T06:50:05.518Z","isFirstParty":false,"canonicalSlug":"agentshelf-xpath-main-content-extractor-b260b29e"}