{"uid":"cap_btR71edbhMSo6JibaU52L","slug":"mcp-security-agentdiet-dev-web-url-markdown-distiller-with-bm25-816abe29","name":"Web URL 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-security.agentdiet.dev/v1/markdown-distill)","url":"https://mcp-security.agentdiet.dev/v1/markdown-distill?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_RMN3x-npCOw7dFqhHAR4_","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 and distills a webpage URL or raw HTML into compact, token-efficient markdown, structured JSON, skeleton outlines, or BM25-focused excerpts for AI agent consumption","exampleAgentPrompt":"Distill the webpage at https://stripe.com/docs/payments into compact markdown using budget mode, focused on 'payment intents', and keep it under 500 tokens.","exampleUseCases":[{"title":"Token-budget research for LLM pipelines","prompt":"Fetch https://openai.com/research/gpt-4 and distill it into markdown mode, keeping it under 300 tokens — I want the key facts without blowing my context window."},{"title":"Structured data extraction from a product page","prompt":"Pull the content from https://aws.amazon.com/ec2/pricing/ and return it in structured mode so I can see the pricing tables cleanly without all the surrounding HTML noise."},{"title":"BM25-focused excerpt for due diligence","prompt":"Distill https://www.sec.gov/cgi-bin/browse-edgar?action=getcompany&CIK=TSLA in budget mode with a query focused on 'risk factors' and cap the output at 400 tokens."}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled content (markdown text, structured JSON tables/metadata, skeleton outline, or BM25-ranked excerpt depending on mode), plus an 'roi_proof' object showing raw_tokens, distilled_tokens, tokens_saved, compression_ratio_pct, roi_multiplier, and llm_cost_saved_usd. Also includes optional cache hit/miss status and billing details.","failureModes":["Invalid or unreachable URL returns fetch error","HTML payload too large may exceed processing limits","mode=budget without a query or max_tokens may return unfiltered output","Paywalled or JavaScript-heavy pages may yield incomplete distillation","Missing required 'url' parameter returns validation error","Rate limiting or payment failure returns HTTP 402"],"whenToPreferThis":"Choose this endpoint when you need to reduce token consumption from web content in an LLM pipeline, especially when operating under strict context window budgets. It is preferable over raw HTTP fetch when you need clean markdown, structured tables, or BM25-ranked excerpts rather than raw HTML. The built-in ROI proof and compression metrics make it ideal for agents that need to justify or track LLM cost savings. Use it over generic scrapers when token efficiency and structured output modes matter.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T15:01:50.031Z","isFirstParty":false,"canonicalSlug":"mcp-security-agentdiet-dev-web-url-markdown-distiller-with-bm25-816abe29"}