{"uid":"cap_SN5ifCCbBakoyIygcBVH3","slug":"mcp-compiler-agentdiet-dev-web-url-distillation-bm25-budget-extraction-a9246281","name":"Web URL Distillation & BM25 Budget Extraction","description":"Distill a URL or raw HTML payload with BM25 budget control (Live x402 v2, IETF MPP & MCP endpoint at https://mcp-compiler.agentdiet.dev/v1/paywall-clean-extract)","url":"https://mcp-compiler.agentdiet.dev/v1/paywall-clean-extract?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_QQcMCRZgXGI1tUjHSc_fL","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-compiler.agentdiet.dev","brandSlug":"mcp-compiler-agentdiet-dev-mpp","brandBaseUrl":"https://mcp-compiler.agentdiet.dev","brandDocsUrl":null,"whatItDoes":"Fetches a webpage (or accepts raw HTML) and distills it into compact, agent-ready tokens using markdown, structured, skeleton, or BM25 budget-controlled modes","exampleAgentPrompt":"Can you fetch https://stripe.com/docs/payments and distill it into clean markdown, keeping it under 2000 tokens focused on the topic 'payment intents'?","exampleUseCases":[{"title":"Research digest within token budget","prompt":"Grab https://en.wikipedia.org/wiki/Transformer_(machine_learning_model) and give me the most relevant content about 'attention mechanisms' in budget mode, capped at 500 tokens."},{"title":"Structured data extraction from docs page","prompt":"Fetch https://docs.openai.com/api-reference and distill it in structured mode so I can see the key tables and metadata without wading through all the prose."},{"title":"Skeleton outline of a long article","prompt":"Pull https://www.nytimes.com/2024/01/15/technology/ai-regulation.html and give me a skeleton outline of the article structure so I can decide if it's worth reading in full."}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled content (markdown text, structured tables/metadata, skeleton outline, or BM25-ranked excerpt depending on mode), plus an 'roi_proof' object showing raw token count, distilled token count, tokens saved, compression ratio percentage, and estimated LLM cost saved in USD. Also includes cache status (HIT/MISS) and billing details.","failureModes":["Invalid or unreachable URL returns an error status","Paywalled or bot-blocked pages may return empty or partial content","max_tokens below minimum of 20 causes validation error","mode=budget without a query parameter may yield suboptimal results","Very large HTML payloads may hit processing limits","Network timeouts on slow external pages"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to read web content but must stay within token or cost budgets — especially for long documentation pages, news articles, or HTML-heavy sites. The BM25 budget mode is uniquely useful when you have a specific query focus and want only the most relevant passage within a strict token ceiling. Prefer this over raw fetch+parse approaches when compression ratio and LLM cost savings matter to your pipeline.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T12:51:18.349Z","isFirstParty":false,"canonicalSlug":"mcp-compiler-agentdiet-dev-web-url-distillation-bm25-budget-extraction-a9246281"}