{"uid":"cap_EAPrfAnUnP2-MbC2Dhirb","slug":"fetchharbor-url-scraper-51b6cf35","name":"FetchHarbor URL Scraper","description":"Fetch one public HTTP(S) URL for research, extraction, or agent workflows. Returns the final URL, upstream status, content type, and decoded content. Private, local, metadata, and reserved destinations are blocked; redirects are revalidated and response size and duration are bounded.","url":"https://fetchharbor.benlab.download/scrape","method":"GET","headers":{},"bodySchema":{"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":["url"],"properties":{"url":{"type":"string","format":"uri"}},"additionalProperties":false}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object","required":["status","url","status_code","content_type","content"],"properties":{"url":{"type":"string","format":"uri"},"status":{"type":"string","const":"success"},"content":{"type":"string"},"status_code":{"type":"integer","maximum":599,"minimum":100},"content_type":{"type":["string","null"]}},"additionalProperties":false}}}}},"responseSchema":null,"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.01","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":"$0.01/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.01","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.01","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_9vU0OrTZTCr31DHe45DNt","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.01","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Fetches the content of a single public HTTP(S) URL and returns the final URL, HTTP status, content type, and decoded body text.","exampleAgentPrompt":"Can you fetch the contents of https://en.wikipedia.org/wiki/Large_language_model and give me the raw page text?","exampleUseCases":[{"title":"Live webpage content lookup","prompt":"Grab the content at https://www.ycombinator.com/companies and give me everything on the page so I can see which companies are listed."},{"title":"Research article retrieval","prompt":"Fetch the full text at https://arxiv.org/abs/2303.08774 so I can read what the paper says without opening a browser."},{"title":"Agent workflow web access","prompt":"Pull the HTML from https://news.ycombinator.com and extract the top story titles from whatever the page contains."}],"resultDescription":"Returns a JSON object containing: the final resolved URL (after any redirects), a success/failure status string, the upstream HTTP status code (100–599), the content-type header value (or null), and the fully decoded body content as a string. Response size and duration are bounded server-side.","failureModes":["Private, localhost, link-local, or reserved IP destinations are blocked and return an error","Redirect chains that resolve to blocked destinations are rejected after revalidation","Response body exceeds size limit — truncated or rejected","Upstream server timeout — duration bound exceeded","Invalid or malformed URL returns a validation error","Non-public schemes (e.g. ftp://, file://) are not supported","Upstream server returns 4xx/5xx which is forwarded in the status_code field"],"whenToPreferThis":"Use this endpoint when an agent needs to retrieve the raw content of a single known public URL — for example, reading a live webpage, fetching an article, or accessing a remote resource as part of a research or extraction pipeline. It is a good fit when privacy-safe, sandboxed web access is needed with bounded response size and redirect revalidation built in. Prefer it over general HTTP clients when you want server-side blocking of private/reserved IP ranges for safety. Not suited for crawling entire sites, authenticated pages, or non-HTTP resources.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-15T12:43:16.422Z","isFirstParty":false}