{"uid":"cap_2_CqDg7whfQVhnhPEKDlM","slug":"mcp-compiler-agentdiet-dev-dom-stripper-bm25-web-distiller-1b0c0b62","name":"DOM Stripper – BM25 Web 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/dom-stripper)","url":"https://mcp-compiler.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_j-djcVkAIawLqoAmT0XU7","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 a URL or raw HTML into compact, agent-ready tokens using configurable modes including BM25 budget-controlled extraction","exampleAgentPrompt":"Can you fetch https://stripe.com/docs/payments and distill it into budget mode focused on 'payment intents', keeping it under 500 tokens?","exampleUseCases":[{"title":"Stripe docs for agent context","prompt":"Pull the Stripe docs from https://stripe.com/docs/api and distill them into markdown mode so I can feed them into my agent without blowing my context window."},{"title":"BM25 budget excerpt for research","prompt":"Fetch https://openai.com/research/gpt-4 and give me only the parts about 'safety evaluations' using budget mode with a max of 300 tokens."},{"title":"Structured data from a landing page","prompt":"Take the HTML from this SaaS pricing page and distill it into structured mode so I can extract the pricing tiers as JSON tables: https://example.com/pricing."}],"resultDescription":"Returns a 'data' object containing the distilled content in the requested mode (Markdown text, structured JSON tables/metadata, skeleton outline, or BM25-focused excerpt), plus an 'roi_proof' object with raw_tokens, distilled_tokens, tokens_saved, compression_ratio_pct, roi_multiplier, and llm_cost_saved_usd. Also includes optional cache hit/miss info and billing details.","failureModes":["URL unreachable or returns non-200 status — endpoint may error or return empty data","HTML too large for processing — may exceed internal limits","BM25 query not provided when mode=budget — query is required for budget mode to focus extraction","max_tokens set below 20 — rejected by schema validation","Invalid mode enum value — rejected before processing","Payment not settled via x402 — 402 response returned before execution"],"whenToPreferThis":"Choose this endpoint when you need to aggressively compress web content to fit within LLM context windows, especially when you want BM25-guided relevance filtering to keep only the tokens that matter for a specific query. It is particularly valuable for agentic pipelines that read many URLs, need to minimize LLM inference costs, or require structured/skeleton extraction rather than raw HTML. Prefer it over generic scrapers when token budget control and compression ROI metrics are important.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:21:00.424Z","isFirstParty":false,"canonicalSlug":"mcp-compiler-agentdiet-dev-dom-stripper-bm25-web-distiller-1b0c0b62"}