{"uid":"cap_c5i_sjbWHqiK2FvGQ7sfH","slug":"mcp-security-agentdiet-dev-web-url-distiller-with-bm25-budget-control-95b01e77","name":"Web URL 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/rag-chunk)","url":"https://mcp-security.agentdiet.dev/v1/rag-chunk?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_CTARhignhvZQKzu_Am7XS","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 URL or raw HTML and distills it into compact, agent-ready tokens using configurable extraction modes and BM25-ranked budget control","exampleAgentPrompt":"Can you distill https://stripe.com/docs/payments/checkout into compact markdown, keeping it under 500 tokens and focusing on the BM25 query 'payment session creation'?","exampleUseCases":[{"title":"RAG pipeline page ingestion","prompt":"Fetch https://openai.com/blog/gpt-4o and distill it into clean markdown under 300 tokens focused on 'multimodal capabilities' so I can add it to my knowledge base without blowing my context window."},{"title":"Competitor pricing page extraction","prompt":"Pull the content from https://anthropic.com/pricing and convert it into structured JSON tables so I can see all their model tiers and costs in a clean format."},{"title":"Tech doc skeleton for navigation","prompt":"Distill https://docs.aws.amazon.com/lambda/latest/dg/welcome.html into a skeleton outline so I can see the high-level structure of the Lambda docs without reading the whole thing."}],"resultDescription":"Returns a data object containing distilled content in the requested format (Markdown, structured JSON, skeleton outline, or BM25-ranked excerpt), along with ROI proof metrics showing raw vs. distilled token counts, tokens saved, compression ratio, cost savings estimate, and optional cache hit/miss status and billing details.","failureModes":["Invalid or unreachable URL returns an error status","max_tokens set below minimum of 20 causes validation failure","BM25 query provided without mode=budget may be ignored","Raw HTML too large may cause processing delays or truncation","Paywalled or JavaScript-heavy pages may produce incomplete distillation","Missing required 'url' parameter returns a schema validation error"],"whenToPreferThis":"Choose this endpoint when you need to reduce token consumption before feeding web content into an LLM, especially in RAG pipelines where context window size matters. It is particularly useful when you need BM25-ranked excerpts focused on a specific topic, or when you want structured or skeleton output rather than raw HTML. Prefer it over generic scraping tools when token efficiency and agent-readiness of output are priorities.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:23:28.011Z","isFirstParty":false,"canonicalSlug":"mcp-security-agentdiet-dev-web-url-distiller-with-bm25-budget-control-95b01e77"}