{"uid":"cap_KSFg7x1-VKCofXTMY81RV","slug":"mcp-compiler-agentdiet-dev-html-url-to-markdown-distiller-with-bm25-576e0f5a","name":"HTML/URL to Markdown Distiller with BM25 Budget Control","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/html-to-markdown)","url":"https://mcp-compiler.agentdiet.dev/v1/html-to-markdown?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_WlO-DR64fMdB6MqRgF_po","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 URL or raw HTML and converts it into compact, agent-ready Markdown (or structured JSON, skeleton, or BM25-focused excerpt) with token compression metrics","exampleAgentPrompt":"Can you fetch https://stripe.com/docs/payments and distill it into compact markdown, staying under 2000 tokens and focusing on the query 'payment intents API'?","exampleUseCases":[{"title":"Research page within token budget","prompt":"Grab https://docs.openai.com/api-reference and distill it into budget mode, focused on 'function calling', keeping it under 1500 tokens so it fits in my context window."},{"title":"Convert documentation to structured tables","prompt":"Fetch https://coinbase.com/developer-platform and convert the page into structured JSON tables so I can parse the feature list programmatically."},{"title":"Get skeleton outline of a long page","prompt":"Pull https://en.wikipedia.org/wiki/Large_language_model and give me just the skeleton outline — section headings and hierarchy — without all the body text."}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled content (Markdown text, structured JSON tables, skeleton outline, or BM25-scored excerpt), an 'roi_proof' object showing raw token count, distilled token count, tokens saved, compression ratio percentage, ROI multiplier, and estimated LLM cost saved in USD, plus optional cache hit/miss status and billing details.","failureModes":["Invalid or unreachable URL returns an error status","URL requires JavaScript rendering and static fetch fails","max_tokens set below minimum of 20 causes validation error","mode=budget without a query parameter may return unfiltered content","Rate limiting or payment failure (HTTP 402) if agent lacks sufficient balance","HTML content too large may hit internal processing limits"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to read and process web pages but must stay within strict token budgets, or when raw HTML is too noisy and verbose for direct LLM consumption. Particularly valuable when you need BM25-focused extraction to retrieve only the most query-relevant content from a long page, or when you want structured JSON tables or skeleton outlines rather than raw text. Prefer over generic scrapers when token efficiency and ROI metrics matter for cost tracking.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:26:11.360Z","isFirstParty":false,"canonicalSlug":"mcp-compiler-agentdiet-dev-html-url-to-markdown-distiller-with-bm25-576e0f5a"}