{"uid":"cap_AXj96_6_cgJzIX7C4AlWq","slug":"axongate-web-page-reader-c84f19ce","name":"AxonGate Web Page Reader","description":"Fetch one public web page and return clean, LLM-ready Markdown with title, word count, content hash and a prompt-injection risk scan of the page text. Use it when an agent needs to read a URL without ingesting scripts, boilerplate or hidden instructions.","url":"https://api.axongate.one/v1/read?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","HEAD","DELETE"],"type":"string"},"queryParams":{"type":"object","required":["url"],"properties":{"url":{"type":"string","description":"Absolute public http(s) URL to read."},"render":{"type":"boolean","description":"Allow rendered fallback for JavaScript-heavy pages (default true)."},"max_chars":{"type":"integer","description":"Truncate markdown to this many characters (default 60000, max 200000)."}}}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object"}}}}},"responseSchema":null,"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.002","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":"$0.002/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.002","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.002","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_2vWwEriCkyeDcqVvcPOVr","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.002","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Fetches a single public web page and returns clean, LLM-ready Markdown with title, word count, content hash, and a prompt-injection risk scan of the page text.","exampleAgentPrompt":"Can you read the page at https://example.com/article and give me the clean text content, making sure to flag any suspicious prompt injection attempts hidden in the page?","exampleUseCases":[{"title":"Research article without boilerplate","prompt":"Fetch the article at https://techcrunch.com/2024/05/01/openai-update and give me just the clean readable content — no ads, nav menus, or scripts."},{"title":"Safety check before citing a source","prompt":"Before I quote from https://randomsite.io/claims, can you read that page and tell me if it contains any hidden prompt-injection instructions I should know about?"},{"title":"Feed a doc page to an agent pipeline","prompt":"Pull the content from https://docs.stripe.com/api/charges and convert it to clean markdown so I can feed it into my summarization workflow — truncate to 40000 characters."}],"resultDescription":"Returns clean Markdown of the page's main content, stripped of scripts and boilerplate, along with the page title, total word count, a hash of the content for deduplication, and a prompt-injection risk assessment of the raw page text.","failureModes":["URL is not publicly accessible or returns a non-200 status — fetch fails with an error","Page is heavily JavaScript-rendered and render fallback is disabled — content may be incomplete","max_chars limit is exceeded — content is truncated at the specified character count","Prompt injection scan may produce false positives on pages with legitimate instructional content","Rate limits or payment failures (x402) prevent the request from completing"],"whenToPreferThis":"Choose this endpoint when an agent needs to safely read a single public URL and get clean, LLM-ready Markdown — especially when prompt-injection risk from untrusted web content is a concern. It is preferable over raw HTTP fetches or generic scrapers because it strips scripts and boilerplate, provides a content hash for deduplication, and actively scans for hidden adversarial instructions embedded in the page.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-30T12:31:04.853Z","isFirstParty":false,"canonicalSlug":"axongate-web-page-reader-c84f19ce"}