MCP Windows Website Downloader Server
Загрузчик веб-сайта MCP
Простой MCP-сервер для загрузки веб-сайтов с документацией и подготовки их к индексации RAG.
Функции
Загружает полные сайты документации, во всяком случае большие куски.
Сохраняет структуру ссылок и навигацию, не совсем. lol
Загружает и организует ресурсы (CSS, JS, изображения), но не очень дружелюбен к ИИ и, вероятно, все это требует некоторого анализа или векторизации в базу данных или чего-то в этом роде.
Создает чистый индекс для систем RAG, в настоящее время, похоже, создает индекс в каждой папке, даже не смотрел на это.
Простой специализированный интерфейс MCP, да.
Related MCP server: Skrape MCP Server
Установка
Сделайте форк и загрузите, перейдите в репозиторий.
uv venv
./venv/Scripts/activate
pip install -e .Добавьте это в ваш claude_desktop_config.json с вашими собственными путями:
"mcp-windows-website-downloader": {
"command": "uv",
"args": [
"--directory",
"F:/GithubRepos/mcp-windows-website-downloader",
"run",
"mcp-windows-website-downloader",
"--library",
"F:/GithubRepos/mcp-windows-website-downloader/website_library"
]
},
Другое использование, о котором вам не нужно беспокоиться и которое может быть галлюцинаторным, лол:
Запустите сервер:
python -m mcp_windows_website_downloader.server --library docs_libraryИспользование через Claude Desktop или другие клиенты MCP:
result = await server.call_tool("download", {
"url": "https://docs.example.com"
})Структура вывода
docs_library/
domain_name/
index.html
about.html
docs/
getting-started.html
...
assets/
css/
js/
images/
fonts/
rag_index.jsonРазработка
Сервер соответствует стандартной архитектуре MCP:
src/
mcp_windows_website_downloader/
__init__.py
server.py # MCP server implementation
core.py # Core downloader functionality
utils.py # Helper utilitiesКомпоненты
server.py: Основная реализация сервера MCP, которая обрабатывает регистрацию инструментов и запросыcore.py: основная функциональность загрузки веб-сайта с правильной обработкой ресурсовutils.py: Вспомогательные утилиты для обработки файлов и URL-адресов
Принципы проектирования
Единая ответственность
Каждый модуль имеет одну ясную цель
Сервер обрабатывает интерфейс MCP
Ядро обрабатывает загрузку
Utils выполняет общие операции
Чистая структура
Сохраняет исходную структуру сайта
Организует активы по типу
Создает понятный индекс для систем RAG
Надежная работа
Правильная обработка ошибок
Разумные пределы глубины
Проверка загрузки активов
Чистая обработка URL/путей
Индекс РАГ
Файл rag_index.json содержит:
{
"url": "https://docs.example.com",
"domain": "docs.example.com",
"pages": 42,
"path": "/path/to/site"
}Внося вклад
Форк репозитория
Создать ветку функций
Внесите изменения
Отправить запрос на извлечение
Лицензия
Лицензия MIT — см. файл LICENSE
Обработка ошибок
Сервер обрабатывает распространенные проблемы:
Недействительные URL-адреса
Ошибки сети
Сбои при загрузке активов
Неправильный HTML
Глубокая рекурсия
Ошибки файловой системы
Ответы об ошибках имеют следующий формат:
{
"status": "error",
"error": "Detailed error message"
}Успешные ответы:
{
"status": "success",
"path": "/path/to/downloaded/site",
"pages": 42
}Available Tools
1 tooldownloadC
Download documentation website for RAG indexing
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | Documentation site URL |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden for behavioral disclosure. It mentions downloading for RAG indexing, implying a read operation, but doesn't specify what gets downloaded (e.g., files, content), permissions needed, rate limits, or output format. This leaves significant behavioral gaps.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence with no wasted words, clearly front-loading the core action and purpose. It's appropriately sized for a simple tool.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no annotations, no output schema, and a single parameter with full schema coverage, the description is incomplete. It lacks details on what the download produces (e.g., files, structured data), how it handles errors, or any behavioral traits, making it inadequate for a tool that performs an operation like downloading.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema already documents the single parameter 'url' as 'Documentation site URL'. The description adds no additional parameter details beyond what the schema provides, meeting the baseline of 3 when schema does the heavy lifting.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Download') and the target ('documentation website for RAG indexing'), making the purpose understandable. It doesn't need to distinguish from siblings since none exist, so a 4 is appropriate for clear but not maximally specific purpose.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives, prerequisites, or constraints. It simply states what it does without context for usage decisions.
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
- First observed
download
TDQS
Scored across 1 tool
With only one tool, there is no possibility of confusion or overlap between tools. The single tool has a clear and distinct purpose.
A single tool inherently has perfect naming consistency, as there are no other tools to compare it against for patterns or conventions.
One tool is too few for a server named 'MCP Windows Website Downloader Server', which suggests a scope that might include operations like listing available websites, configuring downloads, or managing downloaded content. A single download tool feels thin and incomplete for this domain.
The tool surface is severely incomplete for the implied domain of downloading Windows documentation websites. It lacks essential operations such as listing available websites, checking download status, managing or deleting downloaded content, or configuring download parameters, which are likely needed for effective RAG indexing workflows.
Maintenance
Related MCP Connectors
Turn any public website into an MCP server for agents to search, read and navigate.
Deterministic Zero-LLM Web Compiler, Scraper, Crawler, and Site Mapper for AI Agents.
1- fastCRWOAuthio.github.us
Scrape, crawl, map & search the web. Open-source, self-hostable Rust crawler & search for AI agents.
Shared copies of public web pages for AI agents. Search stored pages or fetch a URL.
Related MCP Servers
- FlicenseBqualityDmaintenanceProvides a tool to download entire websites using wget. It preserves the website structure and converts links to work locally.1156-

Skrape MCP Serverofficial
AlicenseBqualityDmaintenanceThis server converts webpages into clean, structured Markdown optimized for language model consumption, removing unnecessary content and supporting JavaScript rendering.112MIT- AlicenseNot gradedqualityCmaintenanceEnables AI agents to clone entire websites, download files, manage authentication sessions, and analyze site information with support for JavaScript-heavy SPAs and dynamic content.9Apache 2.0
- FlicenseNot gradedqualityDmaintenanceA locally-hosted MCP server that provides AI assistants with advanced web crawling capabilities, including structured data extraction, deep site crawling, and page screenshots. It enables users to convert single or multiple URLs into clean Markdown content for processing by LLMs without requiring external API keys for basic features.-