{"uid":"cap_MXIfXFbW-fmALd-u4nMgZ","slug":"mdataaccess-multi-page-website-crawler-9610e24d","name":"MDataAccess Multi-Page Website Crawler","description":"Start a multi-page website crawl of up to 20 pages.","url":"https://api.mdataaccess.com/crawl","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","description":"Root URL of the website to crawl."},"limit":{"type":"integer","maximum":20,"minimum":1,"description":"Maximum number of pages to crawl."}}}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object","required":["provider","url","success"],"properties":{"url":{"type":"string"},"success":{"type":"boolean"},"crawl_id":{"type":["string","null"]},"provider":{"type":"string"},"status_url":{"type":["string","null"]}}}}}}},"responseSchema":null,"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.12","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":"$0.12/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.12","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.12","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_rNgGAQ18--nUGgTBdJONb","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.12","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Initiates a multi-page website crawl of up to 20 pages starting from a root URL, returning a crawl job ID and status tracking URL.","exampleAgentPrompt":"Can you crawl the entire MDataAccess website at https://www.mdataaccess.com and pull content from up to 15 pages so I can review what's on the site?","exampleUseCases":[{"title":"Competitor website content audit","prompt":"Crawl https://www.competitor.com and grab content from up to 20 pages — I want to see everything they publish about their product features."},{"title":"Blog archive extraction","prompt":"Can you crawl https://www.techblog.io starting from the homepage and collect content from up to 10 pages? I want to compile all their recent articles."},{"title":"Documentation site indexing","prompt":"I need you to crawl the docs site at https://docs.someproject.com across up to 20 pages so I can index all the documentation content for search."}],"resultDescription":"Returns a JSON object containing a crawl_id (string or null), a status_url for polling the crawl progress (string or null), the provider name, the root URL that was crawled, and a success boolean indicating whether the crawl job was successfully initiated.","failureModes":["Invalid or unreachable root URL returns success:false with null crawl_id","Page limit out of range (below 1 or above 20) causes validation error","Target website blocks crawlers (robots.txt or rate limiting) may result in partial or failed crawl","Payment failure via x402 protocol prevents job initiation","Network timeout on the root URL results in a failed job start"],"whenToPreferThis":"Use this endpoint when you need to extract content from multiple pages of a website in a single operation rather than scraping pages one by one. Prefer this over the single-page scrape endpoint when the goal is to systematically collect or index content across an entire domain or section of a site. It is especially useful for content audits, documentation indexing, or competitive research where breadth across pages matters more than depth on a single URL.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-14T06:30:06.299Z","isFirstParty":false}