Webscraper MCP

MCP server that transcribes webpages for LLMs to use by providing the url to the LLM.

Catalog onlyCatalog onlySTDIO

Overview

Webscraper MCP is a server designed to transcribe web pages for large language models (LLMs) by providing the URL of the content to be scraped. It can also extract transcripts from YouTube videos and convert PDF documents into markdown text.

To use Webscraper MCP, provide the URL of the webpage, YouTube video, or PDF document you want to scrape. The server will return the text content or transcript based on the provided link.

Extracts text content from web pages. - Retrieves transcripts from YouTube videos. - Converts PDF files into markdown text.

Scraping text from articles for research purposes.
Extracting transcripts from educational YouTube videos for study materials.
Converting PDF reports into editable markdown format for easier manipulation.

Add to your AI client

Use these steps to connect Webscraper MCP in Cursor, Claude, VS Code, and other MCP-compatible apps. The same JSON appears in the Use with menu above for one-click copy.

Cursor

Add this to your .cursor/mcp.json file in your project root, then restart Cursor.

.cursor/mcp.json

{
  "mcpServers": {
    "webscraper-saishridhar": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-webscraper-saishridhar"
      ]
    }
  }
}

Claude Desktop

Add this server entry to the mcpServers object in your Claude Desktop config, then restart the app.

~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows)

{
  "mcpServers": {
    "webscraper-saishridhar": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-webscraper-saishridhar"
      ]
    }
  }
}

Claude Code

Add this to your project's .mcp.json file. Claude Code will detect it automatically.

.mcp.json (project root)

{
  "mcpServers": {
    "webscraper-saishridhar": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-webscraper-saishridhar"
      ]
    }
  }
}

VS Code (Copilot)

Add this to your .vscode/mcp.json file. Requires the GitHub Copilot extension with MCP support enabled.

.vscode/mcp.json

{
  "servers": {
    "webscraper-saishridhar": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-webscraper-saishridhar"
      ]
    }
  }
}

Windsurf

Add this to your Windsurf MCP config file, then restart Windsurf.

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "webscraper-saishridhar": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-webscraper-saishridhar"
      ]
    }
  }
}

Cline

Open Cline settings, navigate to MCP Servers, and add this server configuration.

Cline MCP Settings (via UI)

{
  "mcpServers": {
    "webscraper-saishridhar": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-webscraper-saishridhar"
      ]
    }
  }
}

FAQ

Can Webscraper MCP handle all types of URLs?

No, it primarily supports web pages, YouTube links, and PDF files.

Is there a limit to the size of the content that can be scraped?

The server can handle standard content sizes, but very large documents may require additional processing time.

Is Webscraper MCP free to use?

Yes! Webscraper MCP is free to use for everyone.

Developer tools