{"uid":"cap_FlpPMgRJTC7JIRoCiSHLw","slug":"mcp-compiler-agentdiet-dev-web-url-distiller-context-bloat-eliminator-a6e8ec50","name":"Web URL Distiller & Context Bloat Eliminator","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/context-bloat-eliminator)","url":"https://mcp-compiler.agentdiet.dev/v1/context-bloat-eliminator?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_3ZD9YKK8jF50_ixRUj2SK","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 down to under 500 tokens using budget mode, focused on the query 'payment intents'?","exampleUseCases":[{"title":"Compressing docs for agent context","prompt":"Grab the OpenAI documentation page at https://platform.openai.com/docs/api-reference and distill it into clean markdown so I can feed it to my agent without blowing my context window."},{"title":"BM25-focused budget excerpt for research","prompt":"I need you to fetch https://en.wikipedia.org/wiki/Retrieval-augmented_generation and return only the most relevant 300 tokens about 'vector databases' using budget mode with BM25 focus."},{"title":"Structured data extraction from webpage","prompt":"Pull the page at https://news.ycombinator.com and distill it into structured JSON tables so I can see the top posts and scores in a tidy format."}],"resultDescription":"Returns a 'data' object containing the distilled content (markdown, structured JSON, skeleton outline, or BM25 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. Also includes optional cache hit/miss status and billing details.","failureModes":["URL is unreachable or returns non-200 status — endpoint may return an error status","HTML payload is too large or malformed — distillation may fail or return partial content","max_tokens set below 20 — rejected by schema validation","mode=budget used without a query parameter — BM25 ranking has no anchor","Payment not processed (HTTP 402) — request blocked until x402 micropayment is completed","Builtin URL alias (builtin://stripe-docs) not recognized — returns error"],"whenToPreferThis":"Choose this endpoint when you need to fetch a live webpage and reduce its token footprint before injecting it into an LLM context window. It is especially valuable when working with large documentation pages, news articles, or HTML-heavy sites where raw content would exceed context limits. The BM25 budget mode makes it uniquely suited for query-focused compression when you only need content relevant to a specific topic. Prefer it over generic scrapers when token efficiency and ROI transparency (compression ratio, cost saved) matter to your pipeline.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-21T07:24:26.804Z","isFirstParty":false,"canonicalSlug":"mcp-compiler-agentdiet-dev-web-url-distiller-context-bloat-eliminator-a6e8ec50"}