{"uid":"cap_Tcr0F-CRYQKmkc70ykDYa","slug":"mcp-compiler-agentdiet-dev-semantic-html-pruner-web-url-distiller-f2a1b96f","name":"Semantic HTML Pruner – 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/v1/semantic-html-pruner)","url":"https://mcp-compiler.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_U1DtwQzwGwBCrkoJBk0qb","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":"Can you fetch https://stripe.com/docs/api and distill it into clean markdown, keeping it under 2000 tokens and focusing on the authentication section?","exampleUseCases":[{"title":"Grounding agent on live documentation","prompt":"Grab the content from https://docs.openai.com/api-reference and distill it into structured markdown so I can use it as context — keep it under 3000 tokens."},{"title":"Budget-focused excerpt for RAG pipeline","prompt":"I need a BM25 excerpt from https://en.wikipedia.org/wiki/Transformer_(machine_learning_model) focused on the query 'attention mechanism', and I need it capped at 500 tokens max."},{"title":"Structured data extraction from a news article","prompt":"Pull https://techcrunch.com/2025/06/01/openai-funding-round/ and extract it in structured mode so I get the key metadata and tables without all the HTML noise."}],"resultDescription":"Returns a 'data' object containing the distilled content (Markdown text, structured JSON tables/metadata, a skeleton outline, or a BM25-ranked budget excerpt depending on mode), plus an 'roi_proof' block showing raw_tokens, distilled_tokens, tokens_saved, compression_ratio_pct, and llm_cost_saved_usd. Also includes optional cache status (HIT/MISS) and billing details.","failureModes":["Invalid or unreachable URL returns an error status","mode=budget without a query or max_tokens may return unfiltered or oversized content","Very large HTML pages may hit processing limits or return partial results","Paywalled or bot-blocked sites may return incomplete or empty distillation","max_tokens below 20 is rejected by schema validation","Raw HTML injection via 'html' field with malformed markup may produce degraded output"],"whenToPreferThis":"Choose this endpoint when you need to fetch and compress a live web page or raw HTML into a token-efficient format before passing it to an LLM — especially when context window cost or size is a concern. The BM25 budget mode is uniquely suited for focused retrieval within a strict token ceiling. Prefer this over generic scrapers when you need both fetching and semantic compression in one step, with built-in ROI metrics showing exactly how many tokens were saved.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T12:44:18.837Z","isFirstParty":false,"canonicalSlug":"mcp-compiler-agentdiet-dev-semantic-html-pruner-web-url-distiller-f2a1b96f"}