Imperium RAG-Diet — Web & Document Context Distiller (85-97% Token Savings)
Server Details
Strips 85-97% of HTML/DOM boilerplate into clean Markdown, skeletons, or BM25-ranked RAG chunks.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- Repository
- robertoyanguas-ops/assay
- GitHub Stars
- 0
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 4 tools
Each content tool targets a distinct output form: distill_webpage yields narrative Markdown, extract_structured_data returns JSON-LD/tables/code, and recon_webpage_skeleton returns only a heading outline. The descriptions explicitly cross-reference each other with WHEN TO USE / WHEN NOT TO USE guidance, and get_agent_wallet_status is clearly a separate billing concern.
All four names use consistent snake_case verb_noun structure (distill_webpage, extract_structured_data, get_agent_wallet_status, recon_webpage_skeleton). The only minor deviation is the abbreviated verb 'recon' versus the fully spelled verbs elsewhere, but the pattern remains predictable.
Four tools is well-scoped for a focused distillation service: three content operations (outline, prose, structured) plus one wallet/account tool. Each tool earns its place with no redundancy or filler.
The surface covers the core lifecycle of inspecting a page (recon) and extracting it (prose or structured), plus account/payment handling, with no obvious dead ends for its stated purpose. Minor gaps exist (no batch/multi-URL or crawling operation, and PDF/binary is deliberately excluded), but agents can work around these.
Available Tools
4 toolsdistill_webpageARead-onlyIdempotentInspect
Fetch a public HTTP(S) web page (or accept raw HTML) and distill its main prose into clean Markdown, stripping 85-97% of HTML/JS/CSS boilerplate. WHEN TO USE: Call this tool to read full or query-filtered article and documentation text; call recon_webpage_skeleton first to preview headings and token counts on unfamiliar pages, or extract_structured_data when you need JSON-LD, HTML tables, or code blocks. WHEN NOT TO USE: Do not use for binary PDFs, images, or login-walled pages. PARAMETER INTERACTIONS: Provide either url or html (when html is supplied, url is not fetched and only labels the cache key). When mode='markdown' (default), query and max_tokens are ignored; set mode='budget' to rank sections by query (BM25) and cap output at max_tokens. Omit agent_id and tx_hash during your 5 free calls. Read-only and idempotent; results are cached for 1 hour (<5ms cache hit). $0.001 per call ($0.0005 cached). Pricing: the first 5 calls per agent_id are free and failed calls are never charged. After 5 calls, the tool returns a payment-required quote (not a fatal error) with a $2 Stripe top-up link and Base/Solana USDC addresses; complete payment, then retry with your agd_pass_ key in agent_id or pass tx_hash. Example: distill_webpage(url='https://docs.stripe.com/api')
Inputs: url (required), html, mode, query, +3 more. Returns: data, status, roi_proof
extract_structured_dataARead-onlyIdempotentInspect
Extract machine-readable structured data from a web page: Schema.org JSON-LD objects, OpenGraph metadata, HTML tables parsed as JSON row arrays, fenced code blocks, section headings, and links. WHEN TO USE: Call this tool for pricing tables, API specifications, product metadata, or code snippets; use distill_webpage for narrative Markdown or recon_webpage_skeleton for a lightweight heading outline. WHEN NOT TO USE: Do not use for narrative prose extraction or binary files. PARAMETER INTERACTIONS: Provide either url or html (when html is supplied, url is not fetched and only labels the cache key). Omit agent_id and tx_hash during your 5 free calls. Read-only and idempotent; results are cached for 1 hour (<5ms cache hit). $0.001 per call ($0.0005 cached). Pricing: the first 5 calls per agent_id are free and failed calls are never charged. After 5 calls, the tool returns a payment-required quote (not a fatal error) with a $2 Stripe top-up link and Base/Solana USDC addresses; complete payment, then retry with your agd_pass_ key in agent_id or pass tx_hash. Example: extract_structured_data(url='https://docs.stripe.com/api')
Inputs: url (required), html, tx_hash, agent_id. Returns: data, status, roi_proof
get_agent_wallet_statusARead-onlyIdempotentInspect
Inspect an agent's account ledger: remaining free trial calls (out of 5), prepaid USD balance, cumulative spend, total API calls, and total LLM tokens saved. WHEN TO USE: Call before a batch of paid tool executions or after completing a Stripe or USDC top-up to confirm your balance. WHEN NOT TO USE: Do not use to process web content, execute marketplace tools, or submit payments; use the other tools on this server for execution. PARAMETER INTERACTIONS: Omit agent_id to inspect the default trial account derived from your client IP, or pass your explicit agent_id or agd_pass_ session key to check a specific funded wallet. Free and read-only: never charges a fee or consumes a free trial call. Example: get_agent_wallet_status(agent_id='example')
Inputs: agent_id. Returns: data, status, roi_proof
recon_webpage_skeletonARead-onlyIdempotentInspect
Extract an ultra-compact structural outline (under ~200 tokens) of a web page listing its H1-H4 headings and exact token count per section without returning body prose. WHEN TO USE: Call this tool first on long or unfamiliar pages to inspect structure and token cost before calling distill_webpage (with mode='budget' and a focused query). WHEN NOT TO USE: Do not use when you already need full Markdown prose (use distill_webpage) or structured tables and JSON-LD (use extract_structured_data). PARAMETER INTERACTIONS: Provide either url or html (when html is supplied, url is not fetched and only labels the cache key). Omit agent_id and tx_hash during your 5 free calls. Read-only and idempotent; results are cached for 1 hour (<5ms cache hit). $0.0002 per call. Pricing: the first 5 calls per agent_id are free and failed calls are never charged. After 5 calls, the tool returns a payment-required quote (not a fatal error) with a $2 Stripe top-up link and Base/Solana USDC addresses; complete payment, then retry with your agd_pass_ key in agent_id or pass tx_hash. Example: recon_webpage_skeleton(url='https://docs.stripe.com/api')
Inputs: url (required), html, tx_hash, agent_id. Returns: data, status, roi_proof
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Strips 85-97% of HTML bloat into clean Markdown, <200-token skeletons, or BM25 excerpts via MCP.
Strips 85-97% of HTML/DOM bloat into clean Markdown or JSON with cryptographic ROI proof.
Turn any web page URL or HTML into clean Markdown or plain text for an LLM to read.
Convert any webpage to clean LLM-ready markdown, extraction-first, with article and news modes.
Related MCP Servers
- AlicenseAqualityDmaintenanceCleans HTML from URLs or raw HTML into LLM-ready text, reducing token burn for AI agents.352 npmMIT
- AlicenseAqualityDmaintenanceConverts web pages and HTML strings into clean, LLM-optimized Markdown with metadata extraction and token estimation. It uses a lightweight, browserless approach to provide token-efficient output for more effective LLM processing.2MIT
- AlicenseAqualityBmaintenanceFetch any web page as clean Markdown or plain text, split it into heading-aware, token-bounded RAG chunks, convert raw HTML, and read page metadata. Uses the Web2MD API on RapidAPI with your own key (free BASIC plan).4447 npmMIT
- AlicenseNot gradedqualityAmaintenanceEnables AI agents and LLM pipelines to fetch and crawl webpages, strip extraneous content, and convert them into clean, link-preserving Markdown for fast, token-efficient scraping.MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.