{"uid":"cap_RuBTfJEZ-JG5EmcpLN-by","slug":"context-dev-sitemap-crawler-c9871ccf","name":"Context.dev Sitemap Crawler","description":"Crawls the sitemap of the given domain and returns all discovered page URLs. Supports sitemap index files (recursive), parallel fetching with concurrency control, deduplication, and filters out non-page resources (images, PDFs, etc.).","url":"https://mpp.orthogonal.com/context-dev/web/scrape/sitemap?utm_source=zero.xyz","method":"GET","headers":{},"bodySchema":null,"responseSchema":null,"example":null,"exampleRequest":null,"tags":["scraping","brand","context","extraction","web","data"],"displayCostAmount":"0.03","displayCostAsset":"USDC","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"settled","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":"$0.03/call","primary":{"kind":"static","protocol":"mpp","network":"tempo","amountUsd":"0.03","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"mpp","network":"tempo","amountUsd":"0.03","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_cNhe1ZupoAdxOdXaf2qsF","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.03","costPer":"request","priority":0,"asset":null,"unit":"request","depositMicros":null,"planRef":null}],"brandName":"Context.dev","brandSlug":"context-dev-mpp","brandBaseUrl":"https://www.context.dev","brandDocsUrl":"https://www.context.dev","whatItDoes":"Crawls a domain's sitemap (including recursive sitemap index files) and returns all discovered page URLs","exampleAgentPrompt":"Can you crawl the sitemap for example.com and give me a full list of every page URL it has, including any linked sub-sitemaps?","exampleUseCases":null,"resultDescription":"A list of all page URLs discovered from the domain's sitemap.xml and any linked sitemap index files, returned recursively so no sub-sitemap is missed.","failureModes":["Domain has no sitemap.xml — returns empty result or 404 error","Sitemap is malformed XML — parsing error returned","Domain is unreachable or rate-limiting the crawler — timeout or connection error","Sitemap is extremely large — may hit response size or time limits","Sitemap uses non-standard format not supported by parser"],"whenToPreferThis":"Use this endpoint when you need a complete, structured list of all publicly indexed pages on a domain without having to crawl the site page-by-page. It's ideal for SEO analysis, content audits, competitor research, or pre-flight checks before deeper scraping. Prefer this over general web crawlers when the target site maintains a well-structured sitemap.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-11T00:45:38.656Z","isFirstParty":false,"canonicalSlug":"context-dev-sitemap-crawler-c9871ccf"}