{"uid":"cap_zvImjz3WReyjmXhrNgmo_","slug":"agentdiet-paywall-clean-extract-12068af0","name":"AgentDiet Paywall Clean Extract","description":"Deterministic B2A/A2A/MCP/x402/MPP/L402 execution and intelligence node at https://mcp-gateway.agentdiet.dev settling in USDC on Base.","url":"https://mcp-gateway.agentdiet.dev/v1/paywall-clean-extract?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","POST"],"type":"string"},"queryParams":{"type":"object","properties":{"url":{"type":"string"},"mode":{"type":"string"}}}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object"}}}}},"responseSchema":{"type":"json","example":{"data":{},"status":"ok","roi_proof":{"compression_ratio_pct":91.4}}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.001","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":"$0.001/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.001","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.001","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_nm9APjRXR-788HWs10Xy7","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Fetches a URL and returns clean, compressed text content by stripping paywalls and boilerplate, returning only the core readable content.","exampleAgentPrompt":"Can you fetch the article at https://www.nytimes.com/2024/01/15/tech/ai-news.html and return just the clean readable text, stripping all the ads, navigation, and paywall clutter?","exampleUseCases":[{"title":"Research article content extraction","prompt":"Pull the main article text from https://www.wsj.com/articles/fed-rate-decision-2024 — I just need the clean readable content, no ads or site navigation."},{"title":"Summarize paywalled news piece","prompt":"Grab the clean text from this Bloomberg article https://www.bloomberg.com/news/articles/2024-03-01/markets-update so I can summarize it without all the site boilerplate."},{"title":"Batch content pipeline pre-processing","prompt":"Extract just the body content from https://techcrunch.com/2024/02/10/openai-new-model/ — strip headers, footers, and ads — I need clean text to feed into my analysis pipeline."}],"resultDescription":"Returns a JSON object with a 'data' field containing the extracted clean content, a 'status' field ('ok' on success), and a 'roi_proof' object showing the compression_ratio_pct (e.g. 91.4%), indicating how much boilerplate was removed relative to the original page size.","failureModes":["URL is unreachable or returns a non-200 status — endpoint may return an error status or empty data","Paywall is too aggressive and no meaningful content can be extracted — returns minimal or empty data field","Invalid or malformed URL input — likely returns a validation error","Rate limiting or upstream blocking of the target site — may return error or timeout","Missing required 'input' field in request body — returns schema validation error"],"whenToPreferThis":"Choose this endpoint when you need to extract clean, human-readable text from a webpage or paywalled article with minimal noise. It is especially useful when downstream tasks (summarization, analysis, RAG ingestion) require clean text input without HTML, ads, or navigation. The built-in compression ratio metric helps verify extraction quality. Prefer this over generic scrapers when paywall handling and boilerplate removal are the primary goals.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-22T12:44:13.202Z","isFirstParty":false,"canonicalSlug":"agentdiet-paywall-clean-extract-12068af0"}