{"uid":"cap_yxxLTweMwrIzG2bdPoimR","slug":"mcp-compiler-agentdiet-dev-agentdiet-web-url-distiller-e940d371","name":"AgentDiet Web URL Distiller","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/api/diet)","url":"https://mcp-compiler.agentdiet.dev/api/diet?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_BoC-nl8MxYQM1alZr1_7h","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 compresses it into compact, agent-ready tokens using BM25 budget control and multiple distillation modes","exampleAgentPrompt":"Grab the Stripe docs page at https://stripe.com/docs/payments and distill it into compact markdown — use budget mode with the query 'payment intents' and cap it at 500 tokens so I don't blow my context window.","exampleUseCases":[{"title":"Distill documentation page for agent","prompt":"Take the OpenAI API docs at https://platform.openai.com/docs/guides/embeddings and distill them into clean markdown so I can feed just the relevant parts to my agent — use budget mode focused on 'embedding dimensions' and keep it under 800 tokens."},{"title":"Extract structured data from news article","prompt":"Fetch this TechCrunch article at https://techcrunch.com/2024/05/01/some-article and give me structured tables and metadata from it — I want the author, date, key facts, and any data tables in JSON format."},{"title":"Get skeleton outline of long research paper","prompt":"I have a long HTML report I'll paste in — can you distill it into a skeleton outline so I can see the headings and section structure without reading the whole thing? Use skeleton mode."}],"resultDescription":"Returns a JSON object containing distilled content (Markdown text, structured JSON tables/metadata, skeleton outline, or BM25-ranked budget excerpt depending on mode), along with an ROI proof block showing raw vs distilled token counts, compression ratio, tokens saved, and estimated LLM cost saved. Also includes cache status (HIT/MISS) and billing details.","failureModes":["Invalid or unreachable URL returns an error status","HTML fetch timeout for slow or blocked domains","max_tokens set below minimum of 20 causes validation error","BM25 query missing when mode=budget may return unranked content","Payment/402 failure if x402 micropayment not resolved","Raw HTML too large may be truncated or rejected"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to consume web content without exhausting its context window — especially for documentation pages, news articles, or data-heavy HTML. It is ideal when token cost is a concern and you want measurable compression ratios. Prefer it over generic scrapers when you need multiple distillation modes (markdown, structured, skeleton, budget) or BM25 query-focused extraction. The built-in ROI proof makes it easy to justify token savings in agentic pipelines.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:22:42.431Z","isFirstParty":false,"canonicalSlug":"mcp-compiler-agentdiet-dev-agentdiet-web-url-distiller-e940d371"}