{"uid":"cap_hBVB6n270STyxEXaP3jEM","slug":"mcp-security-agentdiet-dev-agentdiet-semantic-html-pruner-97fd2158","name":"AgentDiet Semantic HTML Pruner","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/semantic-html-pruner)","url":"https://mcp-security.agentdiet.dev/v1/semantic-html-pruner?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_yVKV3QB4w7-PlSH1c66-P","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 URL (or processes raw HTML) and distills it into compact, agent-ready tokens using BM25 budget control and multiple extraction modes","exampleAgentPrompt":"Distill https://stripe.com/docs/payments into compact markdown, keeping it under 1000 tokens and focusing on 'payment intents setup' so I can fit it into my context window.","exampleUseCases":[{"title":"Docs page into LLM context","prompt":"Pull the content from https://docs.openai.com/api-reference and distill it into clean markdown under 800 tokens, focusing on 'authentication and rate limits'."},{"title":"Research article skeleton outline","prompt":"Give me a skeleton outline of https://en.wikipedia.org/wiki/Transformer_(deep_learning_architecture) so I can quickly see its structure without burning through my token budget."},{"title":"Competitive pricing page extraction","prompt":"Fetch https://vercel.com/pricing and extract the structured tables and metadata so I can compare their plans without loading the entire bloated HTML."}],"resultDescription":"Returns a status field, distilled content in the requested format (Markdown, structured JSON tables/metadata, skeleton outline, or BM25-focused excerpt), cache hit/miss info, billing details, and an ROI proof object showing raw vs. distilled token counts, tokens saved, compression ratio percentage, ROI multiplier, and estimated LLM cost saved in USD.","failureModes":["Invalid or unreachable URL returns an error status","Missing required 'url' parameter causes request rejection","mode=budget without a 'query' field may return unfiltered content","max_tokens set below minimum of 20 is rejected","Rate limiting or 402 payment required if billing credentials are absent or insufficient","Paywalled or JavaScript-heavy pages may yield incomplete distillation","Raw HTML supplied with a live URL simultaneously may cause ambiguous behavior"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to consume web page content but must stay within strict token budgets — especially for documentation sites, research pages, or competitor pages where bloated HTML would waste LLM context. The BM25 budget mode makes it uniquely useful when you want to focus distillation on a specific query topic. Prefer it over generic scrapers when token savings and cost reduction are priorities, or when you need structured table/metadata extraction rather than raw HTML.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:21:00.057Z","isFirstParty":false,"canonicalSlug":"mcp-security-agentdiet-dev-agentdiet-semantic-html-pruner-97fd2158"}