F
licenseNot graded
qualityD
maintenanceFetches web pages and converts them to clean, readable markdown format by extracting main content while removing navigation, ads, and other non-essential elements to minimize token usage.
4
-
Mozilla Readability Parser MCP Server
by emzimmer
Mozilla 読みやすさパーサー MCP サーバー
ウェブページのコンテンツを抽出し、LLMに最適化されたクリーンなMarkdownに変換するモデルコンテキストプロトコル（MCP）サーバーです。記事のタイトル、メインコンテンツ、抜粋、署名、サイト名を返します。Mozillaの読みやすさアルゴリズムを使用し、広告、ナビゲーション、フッター、その他の不要な要素を削除しながら、コアコンテンツの構造を維持します。MCPの詳細はこちら。
特徴
広告、ナビゲーション、フッター、その他の不要なコンテンツを削除します
クリーンな HTML をフォーマットされた Markdown に変換します (Turndown も使用)
記事のメタデータ（タイトル、抜粋、署名、サイト名）を返します
エラーを適切に処理する
Related MCP server: cleanfetch
ただフェッチするだけではダメですか?
単純なフェッチ要求とは異なり、このサーバーは次の処理を行います。
Mozilla の読みやすさアルゴリズムを使用して、関連するコンテンツのみを抽出します
広告、ポップアップ、ナビゲーションメニューなどのノイズを排除します
不要なHTML/CSSを削除することでトークンの使用量を削減します
LLM処理を向上させるために一貫したマークダウンフォーマットを提供します
コンテンツに関する有用なメタデータが含まれています
インストール
Smithery経由でインストール
Smithery経由で Claude Desktop 用の Mozilla Readability Parser を自動的にインストールするには:
npx -y @smithery/cli install server-moz-readability --client claude手動インストール
npm install server-moz-readabilityツールリファレンス
parse
Web ページのコンテンツを取得して、クリーンな Markdown に変換します。
引数:
{
"url": {
"type": "string",
"description": "The website URL to parse",
"required": true
}
}戻り値:
{
"title": "Article title",
"content": "Markdown content...",
"metadata": {
"excerpt": "Brief summary",
"byline": "Author information",
"siteName": "Source website name"
}
}Claude Desktopでの使用
claude_desktop_config.jsonに追加します:
{
"mcpServers": {
"readability": {
"command": "npx",
"args": ["-y", "server-moz-readability"]
}
}
}依存関係
@mozilla/readability - コンテンツ抽出
turndown - HTMLからMarkdownへの変換
jsdom - DOM解析
axios - HTTPリクエスト
ライセンス
マサチューセッツ工科大学
Available Tools
1 toolparseA
Extracts and transforms webpage content into clean, LLM-optimized Markdown. Returns article title, main content, excerpt, byline and site name. Uses Mozilla's Readability algorithm to remove ads, navigation, footers and non-essential elements while preserving the core content structure.
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | The website URL to parse |
TDQS
A4/5.0
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It effectively describes key behaviors: the transformation process ('extracts and transforms'), the algorithm used ('Mozilla's Readability algorithm'), what gets removed ('ads, navigation, footers and non-essential elements'), and what is preserved ('core content structure'). However, it doesn't mention potential limitations like rate limits, authentication needs, or error conditions.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is appropriately sized and front-loaded, with two sentences that efficiently convey the tool's purpose, output, and key behavioral traits. Every sentence adds value without redundancy, making it easy to understand at a glance.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's moderate complexity (single parameter, no output schema, no annotations), the description is largely complete. It explains what the tool does, how it processes content, and what it returns. However, without an output schema, it could benefit from more detail on the return structure (e.g., format of the Markdown), and it lacks information on error handling or edge cases.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema description coverage is 100%, with the parameter 'url' clearly documented as 'The website URL to parse'. The description doesn't add any additional meaning or context about the parameter beyond what the schema provides, such as URL format requirements or examples. With high schema coverage, the baseline score of 3 is appropriate.
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?
The description clearly states the tool's purpose with specific verbs ('extracts and transforms') and resources ('webpage content'), specifying the output format ('clean, LLM-optimized Markdown') and what it returns ('article title, main content, excerpt, byline and site name'). It distinguishes itself by mentioning the algorithm used ('Mozilla's Readability algorithm') and what it removes ('ads, navigation, footers and non-essential elements').
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for extracting structured content from webpages, but does not explicitly state when to use this tool versus alternatives, nor provide exclusions or prerequisites. With no sibling tools, the lack of explicit guidelines is less critical, but it still doesn't offer clear when/when-not instructions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
1 tool update
v1.0.0- First observed
parse
TDQS
A3.9/5.0
Scored across 1 tool
Disambiguation5/5
With only one tool, there is no possibility of ambiguity or overlap between tools. The single tool has a clear and distinct purpose focused on parsing webpage content into clean Markdown.
Naming Consistency5/5
A single tool inherently has perfect naming consistency, as there are no other tools to compare against. The tool name 'parse' is straightforward and appropriate for its function.
Tool Count2/5
A single tool is too few for a server's purpose, even if that purpose is narrow. This limits functionality and makes the server feel thin, as it lacks complementary operations like configuration, validation, or batch processing that might be expected in a parsing domain.
Completeness2/5
The tool surface is severely incomplete for a parsing server. While the 'parse' tool covers the core extraction function, there are obvious gaps such as no tools for handling errors, validating inputs, managing configurations, or providing metadata about the parsing process, which could lead to agent failures in real-world scenarios.
Maintenance
ActivityInactive
ResponsivenessUnresponsive
Related MCP Connectors
Convert any webpage to clean LLM-ready markdown, extraction-first, with article and news modes.
Web scraping for AI agents. Converts URLs to clean, LLM-ready Markdown with anti-bot bypass.
Converts any URL to clean, LLM-ready Markdown using real Chrome browsers
Read any public web page as clean Markdown for LLMs, with its metadata. Paid per call, x402.
Related MCP Servers
- AlicenseAqualityCmaintenanceEnables AI agents to read web pages reliably, returning clean markdown content, hyperlinks, and metadata without navigation or ad noise.39 npmMIT
- FlicenseNot gradedqualityDmaintenanceFetches webpages and returns clean, structured Markdown with metadata (title, author, publish date, description, domain, word count).1-
- AlicenseNot gradedqualityDmaintenanceConverts any webpage into clean, LLM-ready Markdown, removing noise and supporting JavaScript rendering.MIT