{"uid":"cap_Or7l1Mv1jDoz40PDmZKfI","slug":"mcp-security-agentdiet-dev-web-url-to-agent-ready-token-distiller-7baadc60","name":"Web URL to Agent-Ready Token Distiller","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/clean-html)","url":"https://mcp-security.agentdiet.dev/v1/clean-html?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_cHB3lrIf6gpklxSsybbJD","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 compresses it into compact, agent-readable markdown, structured JSON, skeleton outline, or BM25-focused budget excerpts with token savings metrics.","exampleAgentPrompt":"Can you fetch https://stripe.com/docs/api and distill it into clean markdown, keeping it under 800 tokens and focusing on the authentication section?","exampleUseCases":[{"title":"Token-budget research briefing","prompt":"Grab the Wikipedia page for transformer neural networks and give me a BM25-focused excerpt about attention mechanisms in under 500 tokens."},{"title":"Structured data extraction from landing page","prompt":"Pull https://openai.com/pricing and distill it into structured JSON tables so I can see the pricing tiers clearly without all the HTML bloat."},{"title":"Skeleton outline for long documentation","prompt":"Fetch https://docs.aws.amazon.com/ec2/index.html and return a skeleton outline of all the main sections — I just need the structure, not the full content."}],"resultDescription":"Returns a JSON object with a 'data' field containing the distilled content (markdown text, structured JSON tables/metadata, skeleton outline, or BM25-focused excerpt depending on mode), plus an 'roi_proof' object showing raw token count, distilled token count, tokens saved, compression ratio percentage, LLM cost saved in USD, and ROI multiplier. Also includes optional cache hit/miss status and billing details.","failureModes":["Invalid or unreachable URL returns an error status","Pages behind authentication or paywalls may return incomplete content","max_tokens set too low may truncate meaningful content","BM25 query with mode other than 'budget' is ignored","Raw HTML that is malformed may produce poor distillation results","Rate limiting or payment failures (402) may block the call"],"whenToPreferThis":"Choose this endpoint when an AI agent needs to ingest web content but must minimize LLM token consumption and cost. It is especially useful when working with large documentation pages, news articles, or any URL where the raw HTML would be too verbose for the agent's context window. The BM25 budget mode makes it uniquely suited for query-focused extraction with a hard token ceiling, distinguishing it from generic web scrapers that return unfiltered content.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T12:45:16.330Z","isFirstParty":false,"canonicalSlug":"mcp-security-agentdiet-dev-web-url-to-agent-ready-token-distiller-7baadc60"}