{"uid":"cap_XX7_ovLzWNU4NwI4hFmDG","slug":"mcp-security-agentdiet-dev-web-url-article-extractor-distiller-09a24951","name":"Web URL Article Extractor & Distiller","description":"Distill a URL or raw HTML payload with BM25 budget control (Live x402 v2, IETF MPP & MCP endpoint at https://mcp-security.agentdiet.dev/v1/article-extractor)","url":"https://mcp-security.agentdiet.dev/v1/article-extractor?utm_source=zero.xyz","method":"GET","headers":{},"bodySchema":{"type":"object","required":["url"],"properties":{"url":{"type":"string","minLength":1,"description":"Target webpage URL to fetch and distill (or builtin://stripe-docs)"},"html":{"type":"string","description":"Optional raw HTML string to distill directly without fetching"},"mode":{"enum":["markdown","structured","skeleton","budget"],"type":"string","default":"markdown","description":"Distillation mode"},"query":{"type":"string","description":"BM25 focus query when mode=budget"},"max_tokens":{"type":"integer","minimum":20,"description":"Strict token budget ceiling when mode=budget"}}},"responseSchema":{"type":"object","required":["status","roi_proof","data"],"properties":{"data":{"type":"object","description":"Distilled Markdown, structured JSON tables/metadata, skeleton outline, or BM25 budget excerpt."},"cache":{"type":"object","properties":{"status":{"enum":["HIT","MISS"],"type":"string"},"cache_key":{"type":"string"},"latency_ms":{"type":"number"}}},"status":{"type":"string","description":"Execution status ('ok')"},"billing":{"type":"object","properties":{"agent_id":{"type":"string"},"payment_method":{"type":"string"},"fee_charged_usd":{"type":"number"}}},"roi_proof":{"type":"object","properties":{"raw_tokens":{"type":"integer"},"tokens_saved":{"type":"integer"},"roi_multiplier":{"type":"number"},"distilled_tokens":{"type":"integer"},"llm_cost_saved_usd":{"type":"number"},"compression_ratio_pct":{"type":"number"}}}}},"example":null,"exampleRequest":null,"tags":[],"displayCostAmount":"0.001","displayCostAsset":"USD","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":"mpp","network":"tempo","amountUsd":"0.001","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"mpp","network":"tempo","amountUsd":"0.001","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_jw5F78J4OuaEymbR0gSUm","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":"mcp-security.agentdiet.dev","brandSlug":"mcp-security-agentdiet-dev-mpp","brandBaseUrl":"https://mcp-security.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a webpage or raw HTML and distills it into compact, agent-ready tokens using BM25 budget control and multiple extraction modes","exampleAgentPrompt":"Can you fetch the article at https://techcrunch.com/2024/05/01/openai-news/ and distill it into clean markdown, keeping it under 500 tokens and focused on the key findings about OpenAI?","exampleUseCases":[{"title":"Research grounding with token budget","prompt":"Grab the content from https://arxiv.org/abs/2405.00001 and distill it into budget mode with a 300-token ceiling, focusing on 'transformer attention mechanisms' so I can use it as context without overflowing my prompt."},{"title":"Structured data extraction from a product page","prompt":"Distill https://stripe.com/docs/payments/checkout into structured mode so I get the tables, metadata, and key sections organized as JSON — I want to programmatically parse the docs."},{"title":"Quick skeleton outline of a long news article","prompt":"Fetch https://www.nytimes.com/2024/04/30/technology/ai-regulation.html and give me just the skeleton outline — I want to see the headings and structure before deciding whether to read the full thing."}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled content (Markdown text, structured JSON tables, skeleton outline, or BM25-focused excerpt depending on mode), plus an 'roi_proof' block showing raw_tokens, distilled_tokens, tokens_saved, compression_ratio_pct, and llm_cost_saved_usd, along with optional cache status and billing info.","failureModes":["Invalid or unreachable URL returns an error status","Paywalled or JavaScript-rendered pages may return empty or incomplete content","Exceeding token budget constraints may truncate content unexpectedly","mode=budget without a query parameter may fall back to full markdown","Raw HTML input that is malformed may produce garbled output","Payment failure (HTTP 402) if the x402 micropayment is not processed"],"whenToPreferThis":"Choose this endpoint when you need to feed live webpage content into an LLM context window efficiently and cost-effectively — especially when token limits are a concern. It is ideal for agents that need to ground responses in real-time web content without manual scraping. The BM25 budget mode makes it uniquely suited for focused, query-relevant excerpts from long pages, distinguishing it from generic scrapers that return raw HTML.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:21:42.624Z","isFirstParty":false,"canonicalSlug":"mcp-security-agentdiet-dev-web-url-article-extractor-distiller-09a24951"}