Diogenes Web Extraction, Readability & Markdown Engine MCP

Web HTML to Clean LLM-Optimized Markdown Engine

extract_clean_markdown

Read-onlyIdempotent

Converts raw HTML into clean, boilerplate-free Markdown with preserved links and headings for LLM context ingestion; use it to replace cluttered web pages with readable article text.

Instructions

Converts raw HTML pages into clean, boilerplate-free, LLM-optimized Markdown with preserved hyperlinks and headings. Use when ingesting raw web documents or blog posts into agent context windows; for isolating tabular data into structured datasets, use parse_html_tables instead. Stateless read-only edge call (max 32 KB, 60 RPM): accepts 'html_content' ('conversion_mode' defaults to 'clean_semantic_article'), supports '?demo=true' or L402 (10 sats), and returns HTTP 400 if invalid.

Input Schema

Name	Required	Description
`html_content`	Yes	Raw HTML string of the web page or document to convert to clean Markdown.
`preserve_links`	No	Whether to retain anchor hyperlinks and image markdown references in output.
`conversion_mode`	No	Markdown extraction strategy: clean semantic article, preserve tables/code, or minimal text.

Output Schema

Name	Required	Description
`title`	Yes	Document title extracted from H1 or title tag.
`markdown`	Yes	Clean, sanitized LLM-ready markdown document.
`word_count`	Yes	Net word count of extracted readable prose.
`links_extracted_count`	Yes	Total hyperlinks preserved in document.

Schema Changelog

Changes observed during successful MCP inspections.

First observedv1.0.0Oct 26, 2026

TDQS

A4.8/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare read-only/idempotent/non-destructive, but the description adds material context the annotations cannot: statelessness, a 32 KB input ceiling, 60 RPM throttling, access via '?demo=true' or L402 payment of 10 sats, and an HTTP 400 failure mode for invalid input. Those are exactly the operational constraints an agent needs before calling a rate-limited, paywalled edge endpoint.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences, front-loaded with purpose then routing, with zero filler. The final sentence is a dense run-on of parentheticals (size cap, rate limit, payment, defaults, error code) that would scan better as a short list, which keeps it from a 5.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return-shape explanation is unnecessary, and the annotations cover the safety profile. The description fills the remaining gaps an agent would care about: input limits, throttling, auth/payment paths, and failure behavior.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3; the description goes slightly beyond by disclosing the default value of 'conversion_mode' ('clean_semantic_article'), which the schema does not declare. It does not otherwise explain the tradeoffs among the three enum modes, so it stops short of a 5.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Converts raw HTML pages into clean, boilerplate-free, LLM-optimized Markdown') and names the exact output characteristics ('preserved hyperlinks and headings'). It also explicitly distinguishes itself from the sibling parse_html_tables, so an agent can route without opening either schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives an explicit use condition ('Use when ingesting raw web documents or blog posts into agent context windows') and an explicit alternative with its own condition ('for isolating tabular data into structured datasets, use parse_html_tables instead'). The when-to-use and the sibling exclusion are both present.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server