Website To Pdf MCP

🚀 Website to PDF/Markdown MCP Server

This MCP server can scrape websites (including those protected by authentication) and convert them into PDF or Markdown documents. It can also traverse links on web pages and include the generated documents or return the discovered URLs.

🚀 Quick Start

This MCP server enables you to scrape websites and convert them into PDF or Markdown documents. It supports authentication and link traversal, providing a flexible solution for web content extraction and conversion.

✨ Features

• Convert a single web page to PDF.
• Convert web pages to Markdown format.
• Traverse links on web pages and convert multiple pages into a single PDF or Markdown file.
• Support authentication via username and password.
• Configurable maximum page limit (for link traversal).
• Traverse website links and return discovered URLs without conversion.

📦 Installation

1. Clone this repository.
2. Install dependencies:

   npm install
   

3. Copy the example environment file:

   cp .env.example .env
   

4. Start the server:

   npm start
   

📚 Documentation

API Endpoints

Convert a Website to PDF

POST /api/convert

Request Body:

{
  "url": "https://example.com",
  "username": "optional-username",
  "password": "optional-password",
  "traverseLinks": true,
  "maxPages": 10
}

Parameters:

• url: (Required) The URL to convert to PDF.
• username: (Optional) Username for authentication.
• password: (Optional) Password for authentication.
• traverseLinks: (Optional) Whether to traverse links on the web page (Default: false).
• maxPages: (Optional) Maximum number of pages to process when traversing links (Default: 10).

Response:

The response will be a PDF document with appropriate Content-Type headers:

Content-Type: application/pdf
Content-Disposition: attachment; filename="example_com.pdf"

The binary PDF content is returned directly in the response body.

Convert a Website to Markdown

POST /api/to-markdown

Request Body:

{
  "url": "https://example.com",
  "username": "optional-username",
  "password": "optional-password"
}

Parameters:

Same as /api/convert.

Response:

The response will be a Markdown document with appropriate Content-Type headers:

Content-Type: text/markdown

The Markdown content is returned directly in the response body.

Traverse a Website and Get URLs

POST /api/get-urls

Request Body:

{
  "url": "https://example.com",
  "username": "optional-username",
  "password": "optional-password"
}

Parameters:

Same as /api/convert.

Response:

The response will be a JSON array containing all discovered URLs:

[
  "https://example.com/page1",
  "https://example.com/page2",
  ...
]

💻 Usage Examples

Basic Usage

For local development, you can use tools like ngrok to expose the local server to the internet:

npm start
# In another terminal
ngrok http 3000

Then use the ngrok URL when setting up the MCP in Claude.

Advanced Usage

Through this MCP server, you can directly use the following functions in conversations with Claude:

1. Convert example.com to PDF.
2. Convert example.com to Markdown.
3. Get all URLs of example.com.
4. Authenticate with the username "myuser" and password "mypass".