{"uid":"cap_QgU1LFrERZ8ieXDR8yFrh","slug":"mcp-security-agentdiet-dev-web-url-to-markdown-distiller-with-bm25-bea14de8","name":"Web URL to Markdown 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/docs-to-markdown)","url":"https://mcp-security.agentdiet.dev/v1/docs-to-markdown?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_zbAvd0y0xgsLw_G-h1P6u","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 raw HTML and distills it into compact, token-efficient markdown, structured JSON, skeleton outline, or BM25-focused budget excerpts for AI agents","exampleAgentPrompt":"Fetch the Stripe docs page at https://stripe.com/docs/api/charges and distill it into compact markdown — use budget mode with a focus query on 'charge creation' and cap it at 2000 tokens so I don't blow my context window.","exampleUseCases":[{"title":"Distill API docs for coding agent","prompt":"Grab the OpenAI API reference at https://platform.openai.com/docs/api-reference and distill it into structured markdown — keep it tight, I want to feed it to my coding agent without burning through my token budget."},{"title":"BM25-focused excerpt from long page","prompt":"Pull https://docs.aws.amazon.com/lambda/latest/dg/welcome.html and give me only the sections relevant to 'cold start performance' — use budget mode, max 1500 tokens."},{"title":"Skeleton outline of competitor landing page","prompt":"Fetch https://www.notion.so/product and return a skeleton outline of the page structure — I just need the headings and key sections, not the full content."}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled content (markdown text, structured JSON tables/metadata, skeleton heading outline, or BM25-filtered excerpt depending on mode), plus an 'roi_proof' object showing raw token count, distilled token count, tokens saved, compression ratio percentage, and estimated LLM cost saved in USD. Optionally includes cache hit/miss status and billing details.","failureModes":["Invalid or unreachable URL returns error status","mode=budget without a query or max_tokens may return unfiltered content","Paywalled or bot-blocked pages may return empty or partial content","Very large pages may exceed internal fetch limits","Invalid HTML in the html parameter may produce garbled output","Missing required 'url' parameter returns a validation error"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to ingest web page content but wants to minimize token usage and LLM costs — especially for long documentation pages, API references, or news articles. The BM25 budget mode makes it uniquely suited for targeted extraction when you have a specific query and a strict token ceiling. Prefer this over raw fetch/scrape tools when compression ROI and cost transparency matter, or when you need structured JSON tables or skeleton outlines rather than raw HTML.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:21:47.120Z","isFirstParty":false,"canonicalSlug":"mcp-security-agentdiet-dev-web-url-to-markdown-distiller-with-bm25-0a37e53f"}