Skip to content

Cursor

Connect Cursor IDE to the CoreClaw MCP Server so your AI coding assistant can search for scrapers, run them, and retrieve data directly within your editor.

Cursor supports MCP via Streamable HTTP transport. You can configure it by creating an mcp.json file in your project or global settings.

Project-level (recommended for team sharing):

.your-project/.cursor/mcp.json

Global (applies to all projects):

~/.cursor/mcp.json

Step 2: Add the CoreClaw MCP configuration

Section titled “Step 2: Add the CoreClaw MCP configuration”
{
"mcpServers": {
"coreclaw": {
"url": "https://mcp.coreclaw.com/mcp",
"headers": {
"api-key": "scraper_api_YOUR_KEY_HERE"
}
}
}
}

Replace scraper_api_YOUR_KEY_HERE with your actual CoreClaw API key.

Cursor IDE MCP Configuration

After saving the configuration, restart Cursor for the changes to take effect.

  1. Open Cursor and start a new chat (Cmd/Ctrl + L)
  2. Switch to Agent mode
  3. Ask: “Search for Amazon scrapers on CoreClaw”
  4. Cursor should invoke search_scrapers and return results

Once connected, you can ask Cursor to perform scraping tasks:

You: Find a Google Maps scraper and extract restaurant data near Central Park, New York.

Cursor: I’ll search for a Google Maps scraper and run it for you. [Calls search_scrapersget_scraper_detailsrun_scraper → polls status → returns results]

  • Restart Cursor — MCP changes require a restart
  • Ensure you’re in Agent mode (not Chat mode)
  • Check that the mcp.json file is in the correct location
  • Ensure the api-key header value matches your CoreClaw API key exactly
  • Verify your key is active in the Console