You:
Add a .mcp.json file to your project root, replacing your-api-key-here with your API key:
{
"mcpServers": {
"nerdydata": {
"command": "npx",
"args": ["-y", "@nerdydata/mcp"],
"env": {
"NERDYDATA_API_KEY": "your-api-key-here"
}
}
}
}| get_suggestions | Find technology report IDs by name (e.g. "Shopify", "Klaviyo"). |
| search_code | Search websites by technology or code snippet. Returns company info, emails, LinkedIn, spend estimates. |
| search_titles | Search websites by their <title> tag content. |
| search_descriptions | Search websites by their <meta description> content. |
| create_download | Queue a full CSV export of matching websites. |
| get_download | Poll a download job by ID. Returns a file URL when ready. |
| get_domain | Look up a domain's metadata: company, employees, spend, emails, social profiles. |
| get_domain_technologies | See what technologies a specific domain uses. |
The NerdyData MCP (Model Context Protocol) Server is a plugin that connects AI assistants like Claude Desktop, Cursor, Windsurf, and ChatGPT to NerdyData. It lets you search websites by technology, look up domain profiles, and export lead lists directly inside your AI workflow.
The NerdyData MCP Server works with any MCP-compatible client, including Claude Desktop, Cursor, Windsurf, and CLI-based MCP clients.
You can search millions of websites by technology or code snippet, look up domain profiles including company name and spend estimates, and export lists of matching websites — all from within your AI assistant.
Installation instructions are available on this page. You will need a NerdyData API key to authenticate.
