Website to PDF/Markdown MCP Server

Name: Website to PDF/Markdown MCP Server
Author: ldangelo

@ldangelo

リポジトリ

Website to PDF/Markdown MCP Server について

MCP server that fetches websites and converts them to PDF, with link traversal support

基本情報

カテゴリ

ファイルとストレージ

ランタイム

node

トランスポート

stdio

公開者

ldangelo

設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "website-to-pdf-mcp": {
      "url": "https://example.com",
      "username": "optional-username",
      "password": "optional-password",
      "traverseLinks": true,
      "maxPages": 10
    }
  }
}

ツール

ツールは検出されませんでした

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

What is Website to PDF/Markdown MCP Server?

An MCP server that fetches websites (including those behind authentication) and converts them to PDF or Markdown documents. It can also traverse links on a webpage and include them in the generated documents or return the discovered URLs.

How to use Website to PDF/Markdown MCP Server?

Self-host the server using Node.js (clone the repo, run npm install, copy .env.example to .env, then npm start). Install it as a plugin in Claude by pointing to your hosted server’s URL. Three API endpoints are available: /api/convert (PDF), /api/to-markdown (Markdown), and /api/traverse (URLs only).

Key features of Website to PDF/Markdown MCP Server

Convert a single webpage to PDF
Convert a webpage to Markdown format
Traverse links on a webpage and convert multiple pages
Support for authentication via username and password
Configurable maximum page limit for link traversal
Traverse website links and return URLs without conversion

Use cases of Website to PDF/Markdown MCP Server

Convert entire documentation websites into a single PDF or Markdown file for offline reading
Archive authenticated content behind login forms as a PDF document
Discover all pages on a website by returning their URLs via link traversal
Extract a blog article and its linked posts into a unified Markdown summary
Combine multiple pages from a site into a single document for research or backup

FAQ from Website to PDF/Markdown MCP Server

What is needed to run the server?

Node.js and npm. After cloning the repo, run npm install, copy .env.example to .env, then start with npm start.

Does the server support authentication?

Yes. You can pass optional username and password fields in the request body. The default implementation assumes a simple username/password form and may need customization for specific sites.

Where does the data live during conversion?

The server converts websites on-demand and returns the generated PDF or Markdown content directly in the response body. It does not store the documents or website data permanently.

How many pages can be traversed at once?

The traversal is limited by the optional maxPages parameter, which defaults to 10. You can adjust this value in the request body.

How are the API endpoints exposed to Claude?

This MCP server is designed as a Managed Claude Plugin. You self-host it on a publicly accessible HTTPS URL, then install it in Claude by providing that URL. Claude automatically discovers the endpoints and creates the plugin interface.