{"uid":"cap_cgvUbxh9QjTZEdO2Gg93x","slug":"agent-tools-web-page-to-markdown-d36f1043","name":"Agent Tools Web Page to Markdown","description":"Read a web page as clean LLM-ready markdown (main content, no nav or scripts) for research, RAG and summarization. Respects robots.txt.","url":"https://agent-tools.jbarkules.workers.dev/v1/web/markdown?utm_source=zero.xyz","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"],"type":"string"},"queryParams":{"type":"object","required":["url"],"properties":{"url":{"type":"string","description":"Public page URL"}}}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object"}}}}},"responseSchema":{"type":"json","example":{"url":"https://example.com/","title":"Example Domain","status":200,"markdown":"This domain is for use in documentation examples...","characters":156}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.0015","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":"$0.0015/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.0015","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.0015","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_mderp5QXzXZnt6Gf1dJ6B","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.0015","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Fetches a public web page and returns its main content as clean, LLM-ready markdown, stripping navigation, scripts, and boilerplate.","exampleAgentPrompt":"Can you fetch the content from https://en.wikipedia.org/wiki/Large_language_model and give it to me as clean markdown, just the main article text without any navigation or sidebars?","exampleUseCases":[{"title":"RAG pipeline document ingestion","prompt":"Pull the main content from https://docs.anthropic.com/en/docs/overview as clean markdown so I can add it to my knowledge base."},{"title":"News article summarization","prompt":"Grab the article at https://www.bbc.com/news/technology-12345678 and convert it to clean markdown — I want to summarize it without all the header and footer clutter."},{"title":"Competitor research content fetch","prompt":"Fetch the page at https://openai.com/research/gpt-4 and return just the readable content as markdown so I can analyze what they're saying."}],"resultDescription":"A JSON object containing the original URL, the page title, the HTTP status code, and the full main-body content of the page rendered as clean markdown — navigation menus, scripts, ads, and boilerplate are stripped, leaving only the primary readable content.","failureModes":["URL is not publicly accessible or returns a non-200 status (reported in status field)","robots.txt disallows crawling — endpoint respects robots.txt and will not fetch the page","Malformed or missing url query parameter returns an error","Page is JavaScript-rendered and content requires a JS engine — static fetcher may return incomplete markdown","Timeout on slow or large pages","URL points to a non-HTML resource (PDF, binary) — use the PDF-specific endpoint instead"],"whenToPreferThis":"Choose this endpoint when you need clean, LLM-ready markdown from a public web page's main body content, with nav and scripts removed — ideal for RAG ingestion, summarization, or research pipelines. Prefer this over a full page reader when you only need body text and not metadata like Open Graph tags or canonical URLs (use the sibling 'one call page reader' endpoint for those). Not suitable for PDF or image documents (use the document parsing or PDF-to-text endpoints), or for pages blocked by robots.txt.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-28T06:35:04.255Z","isFirstParty":false,"canonicalSlug":"agent-tools-web-page-to-markdown-d36f1043"}