{"uid":"cap_jijGqlePw_jAXQlrMejQX","slug":"mcp-security-agentdiet-dev-web-url-dom-distiller-with-bm25-budget-12ad202d","name":"Web URL DOM 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/dom-stripper)","url":"https://mcp-security.agentdiet.dev/v1/dom-stripper?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_7IXyP_4PqlFIpZxm_bSo-","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 a webpage (or accepts raw HTML) and distills it into compact, agent-ready tokens using configurable modes including BM25 query-focused budget extraction","exampleAgentPrompt":"Distill https://stripe.com/docs/payments into clean markdown and keep it under 2000 tokens using budget mode focused on the query 'payment intents'.","exampleUseCases":[{"title":"Compress docs page for agent context","prompt":"Fetch https://docs.openai.com/api-reference and distill it into budget mode with a max of 1500 tokens, focused on the query 'function calling', so I can drop it into my agent's context without burning my token budget."},{"title":"Extract structured data from a landing page","prompt":"Pull the page at https://www.stripe.com/pricing and give me back a structured JSON with all the pricing tables and metadata — I want the clean version without any nav, footer, or ad bloat."},{"title":"Get a skeleton outline of a long article","prompt":"Take this URL https://www.economist.com/technology/2024/01/ai-chips and give me a skeleton outline of the article — just headings and key bullet points — so I can decide if it's worth reading in full."}],"resultDescription":"Returns a JSON object containing: the distilled content (as Markdown, structured JSON tables/metadata, skeleton outline, or BM25-focused excerpt depending on mode); ROI proof metrics (raw token count, distilled token count, tokens saved, compression ratio %, LLM cost saved in USD, ROI multiplier); optional cache metadata (HIT/MISS, latency); and billing details. The core value is a drastically compressed, agent-consumable representation of a webpage.","failureModes":["Invalid or unreachable URL returns an error status","max_tokens too small (below 20) triggers a validation error","BM25 query provided without mode=budget may be ignored","Raw HTML too large may be truncated or rejected","Paywalled or bot-blocked pages may return empty or partial content","Missing required 'url' parameter returns a 400-level error"],"whenToPreferThis":"Choose this endpoint when you need to feed live web content into an LLM context window but want to minimize token usage and cost. It is especially valuable when working with long documentation pages, news articles, or structured web content that contains significant boilerplate. The BM25 budget mode is uniquely suited for query-focused extraction within a strict token ceiling — use it when you know what topic you're looking for. Prefer this over raw fetch + manual parsing when you need markdown, structured tables, or skeleton outlines without writing your own scraper.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:21:49.830Z","isFirstParty":false,"canonicalSlug":"mcp-security-agentdiet-dev-web-url-dom-distiller-with-bm25-budget-12ad202d"}