{"uid":"cap_ZED3eNyGuZdnVC23CWEwf","slug":"mcp-compiler-agentdiet-dev-agentdiet-web-url-distiller-clean-html-62b137b4","name":"AgentDiet Web URL Distiller (clean-html)","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/clean-html)","url":"https://mcp-compiler.agentdiet.dev/v1/clean-html?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_VIj-0nxKafJg-RfU4-v0p","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 web URL or raw HTML and compresses it into compact, agent-ready tokens using BM25-guided budget control and multiple distillation modes.","exampleAgentPrompt":"Distill this URL into compact markdown for me — https://stripe.com/docs/payments — and keep it under 800 tokens using budget mode focused on the query 'payment intents'.","exampleUseCases":[{"title":"Token-budget research from live webpage","prompt":"Fetch https://openai.com/research/gpt-4 and distill it into structured mode so I get tables and metadata — I want to keep the token count low for my pipeline."},{"title":"Extract relevant section from documentation","prompt":"I need just the parts of https://docs.anthropic.com/claude/reference about 'tool use' — distill it in budget mode with a max of 500 tokens focused on that query."},{"title":"Convert raw HTML snippet to clean markdown","prompt":"I've got this raw HTML from a scrape — can you distill it into clean markdown without fetching anything? I'll paste the HTML directly."}],"resultDescription":"Returns a JSON object containing the distilled content (Markdown, structured tables, skeleton outline, or BM25-filtered excerpt), cache hit/miss info, billing details, and an ROI proof block showing raw token count, distilled token count, tokens saved, compression ratio percentage, and estimated LLM cost saved in USD.","failureModes":["Missing or invalid URL returns a validation error","Unreachable or blocked URLs result in fetch failure","mode=budget without a query may return unfiltered content","max_tokens set below minimum (20) triggers a schema validation error","Rate limiting or payment failure may return HTTP 402 if credits are exhausted","Very large pages may exceed processing limits or timeout"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to read a webpage but must stay within a token budget, minimize LLM costs, or receive structured/markdown output rather than raw HTML. It is especially useful when you have a BM25 keyword focus and want only the most relevant excerpt from a long page. Prefer it over generic scrapers when ROI proof (compression ratio, cost saved) is needed, or when you want to pass Stripe docs or other large reference pages to an LLM without blowing your context window.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T12:45:16.322Z","isFirstParty":false,"canonicalSlug":"mcp-compiler-agentdiet-dev-agentdiet-web-url-distiller-clean-html-62b137b4"}