{"uid":"cap_PdKyK2hKeXax11gQ7WKnQ","slug":"mcp-compiler-agentdiet-dev-url-to-markdown-web-distiller-agentdiet-d2d9c0f1","name":"URL to Markdown Web Distiller (AgentDiet)","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/url-to-markdown)","url":"https://mcp-compiler.agentdiet.dev/v1/url-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_g2agM8zW_yKp_HmMtLxxX","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 URL or raw HTML and distills it into compact, agent-ready Markdown, structured JSON, skeleton outline, or BM25-ranked token budget excerpt","exampleAgentPrompt":"Fetch the Stripe pricing page at https://stripe.com/pricing and distill it into compact markdown, keeping it under 1000 tokens — I want just the key content without all the HTML noise.","exampleUseCases":[{"title":"Compress docs page before LLM processing","prompt":"Pull the OpenAI API reference at https://platform.openai.com/docs/api-reference and distill it into a skeleton outline so I can navigate it without blowing my token budget."},{"title":"BM25-focused excerpt from long article","prompt":"Grab https://en.wikipedia.org/wiki/Transformer_(machine_learning_model) and return only the parts most relevant to 'attention mechanism', capped at 500 tokens using budget mode."},{"title":"Distill raw HTML into structured metadata","prompt":"I have this raw HTML from a product page — can you distill it into structured JSON tables so I can extract the pricing and specs without parsing it myself?"}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled content (Markdown, structured JSON, skeleton, or BM25 excerpt), an 'roi_proof' object showing raw vs. distilled token counts, compression ratio, and estimated LLM cost saved, plus optional billing and cache metadata.","failureModes":["URL is unreachable or returns non-200 status — fetch failure error","Invalid or malformed URL provided — validation error","max_tokens set below minimum of 20 — schema validation error","mode=budget used without a query parameter — incomplete BM25 configuration","Requested page blocks bots or requires authentication — empty or partial content returned","Token budget too small to meaningfully represent the content — truncated or minimal output"],"whenToPreferThis":"Choose this endpoint when you need to reduce the token footprint of web content before passing it to an LLM, especially for long documentation pages, articles, or HTML payloads. It is ideal when you need BM25-focused excerpts within a strict token budget, or when you want structured JSON or skeleton outlines rather than raw HTML. Prefer it over generic scrapers when LLM cost savings and compression metrics matter to your workflow.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:24:30.713Z","isFirstParty":false,"canonicalSlug":"mcp-compiler-agentdiet-dev-url-to-markdown-web-distiller-agentdiet-d2d9c0f1"}