{"uid":"cap_C_7zgm2n_za45mFOzJOEN","slug":"mcp-compiler-agentdiet-dev-webpage-distiller-compact-agent-ready-75fdf1cd","name":"Webpage Distiller — Compact Agent-Ready Token Extractor","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/webpage-distiller)","url":"https://mcp-compiler.agentdiet.dev/v1/webpage-distiller?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_FphjVhEXG7tRHnnfKSES8","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 and distills any web URL (or raw HTML) into compact, token-efficient markdown, structured JSON, skeleton outline, or BM25-focused budget excerpt for AI agents.","exampleAgentPrompt":"Distill the content at https://stripe.com/docs/api into compact markdown and tell me how many tokens you saved compared to the raw page.","exampleUseCases":[{"title":"Token-efficient doc ingestion for agents","prompt":"Fetch https://docs.openai.com/api-reference and distill it into markdown so I can inject it into my agent's context without burning through my token budget."},{"title":"BM25-focused research excerpt","prompt":"Grab the page at https://en.wikipedia.org/wiki/Transformer_(machine_learning_model) and give me a budget excerpt focused on 'attention mechanism' with a max of 500 tokens."},{"title":"Structured data extraction from a product page","prompt":"Distill https://www.apple.com/iphone-16-pro/ in structured mode so I get the key specs and metadata as a JSON table I can process programmatically."}],"resultDescription":"Returns a 'data' object containing the distilled content in the requested format (markdown text, structured JSON tables/metadata, skeleton outline, or BM25-ranked excerpt), along with an 'roi_proof' block showing raw token count, distilled token count, tokens saved, compression ratio percentage, estimated LLM cost saved in USD, and an ROI multiplier. Also includes cache status and billing details.","failureModes":["Invalid or unreachable URL returns a fetch error with status non-ok","mode=budget used without providing a 'query' parameter may return unfiltered or error response","max_tokens set below 20 (minimum) rejected with validation error","Paywalled or JS-heavy pages may return incomplete or empty distillation","Missing required 'url' parameter returns a 400-level error","Payment not processed (402) blocks execution if agent lacks x402 credentials"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to consume live web content without exhausting its context window — especially for documentation sites, news articles, or product pages. It is ideal when token cost matters and BM25-budget mode is needed to focus on a specific topic within a large page. Prefer it over generic scraping tools when you need ROI proof of compression or when feeding structured JSON or skeleton outlines to downstream agents.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:23:30.139Z","isFirstParty":false,"canonicalSlug":"mcp-compiler-agentdiet-dev-webpage-distiller-compact-agent-ready-75fdf1cd"}