Website Data Website Data
Features Integrations Pricing
Log in

MCP Server

Contents

Overview

The Website Data MCP server allows AI assistants to access Website Data directly through the Model Context Protocol (MCP). Once connected, you can ask your AI assistant questions about domains and technologies and it will query Website Data to provide answers.

The MCP server is available to all customers with API access. You'll need a Website Data API key, which you can find on your Account page.

Setup

The Website Data MCP server is a remote server hosted at https://websitedata.app/mcp. No installation is required — simply configure your AI client to connect to the server with your API key.

Claude Code (CLI)

Run the following command in your terminal, replacing YOUR_API_KEY with your Website Data API key: 

claude mcp add -t http websitedata https://websitedata.app/mcp -H "Authorization: Bearer YOUR_API_KEY"

You can verify the server was added by running claude mcp list. For more details, see the Claude Code MCP documentation.

Claude Desktop

You can use the Claude Code tab in Claude Desktop to set up the MCP server automatically. Paste the following prompt into Claude Code and it will configure the server for you: 

Check my Node version by running node --version. If it's below v20, stop and let me know I need to upgrade Node first (via brew install node on Mac or nodejs.org on Windows).

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

Add the following MCP server entry (creating the mcpServers key if it doesn't exist, preserving any existing servers):

"websitedata": {
  "command": "npx",
  "args": [
    "mcp-remote",
    "https://websitedata.app/mcp",
    "--header",
    "Authorization: Bearer YOUR_API_KEY"
  ]
}

Important — Node PATH fix for macOS: Claude Desktop is a GUI app and does not inherit your shell's PATH (nvm, Homebrew, etc. are not available). This commonly causes a "File is not defined" or "ReferenceError" crash when the server starts. To fix this:
- Run which node to get the absolute path to your Node binary (e.g. /Users/me/.nvm/versions/node/v24.13.1/bin/node)
- Replace "command": "npx" with the absolute path to npx in the same directory (e.g. "/Users/me/.nvm/versions/node/v24.13.1/bin/npx")
- Add an env block so child processes also use the correct Node:
  "env": { "PATH": "/path/to/your/node/bin:/opt/homebrew/bin:/usr/local/bin:/usr/bin:/bin" }

After Claude sets up the config file, you'll need to replace YOUR_API_KEY with your actual Website Data API key:

  • macOS: Open Finder, press Cmd+Shift+G (Go to Folder), paste ~/Library/Application Support/Claude and press Enter. Open claude_desktop_config.json in a text editor and replace YOUR_API_KEY with your key from the Account page.
  • Windows: Press Win+R, type %APPDATA%\Claude and press Enter. Open claude_desktop_config.json in a text editor and replace YOUR_API_KEY with your key from the Account page.

Restart Claude Desktop after updating the config file for the changes to take effect.

Cursor

In Cursor, open Settings and navigate to the MCP section. Add a new server with the following configuration. For step-by-step instructions, see the Cursor MCP documentation. 

{
  "mcpServers": {
    "websitedata": {
      "type": "streamable-http",
      "url": "https://websitedata.app/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_KEY"
      }
    }
  }
}

Available Tools

The MCP server provides the following tools that AI assistants can use to query Website Data:

get_domain
Look up a single domain by name. Returns title, description, language, country, categories, technologies, rank, and more.
search_domains
Search and filter domains by keyword, country, language, category, technology, TLD, and fingerprints. Supports sorting and cursor-based pagination.
bulk_get_domains
Fetch up to 100 domains in a single request.
get_domains_by_tld
List domains filtered by top-level domain (e.g. "com", "org", "io").
get_technology
Look up a single technology by name. Returns description, URL, icon, categories, and install/uninstall metrics.
search_technologies
Search and filter technologies by keyword and category. Supports sorting by name, total installs, new installs, uninstalls, or net change.

Example Prompts

Once connected, you can ask your AI assistant questions like:

  • "Look up the domain shopify.com"
  • "Search for domains in the US that use WordPress"
  • "Find all .io domains in the technology category"
  • "What technologies does stripe.com use?"
  • "Search for technologies related to analytics"
  • "Find domains that use both Google Analytics and Cloudflare"

For more details about the Website Data API, see the API Documentation.