MCP Web Search & Scrape in Cursor

Add web scraping and search to Cursor in 2 minutes

Connect Firecrawl to Cursor through the hosted MCP server, then sign in with your Firecrawl account.

Quick setup

1. Click Add to Cursor above to open the install dialog in Cursor.
2. Confirm the Firecrawl MCP server installation.
3. Use the server’s sign-in option in Cursor to connect your Firecrawl account and approve access.
4. Confirm that Firecrawl’s tools are available in Cursor.

Prefer to add the configuration manually?

Open Cursor Settings, select MCP, and add:

{
  "mcpServers": {
    "firecrawl": {
      "url": "https://mcp.firecrawl.dev/v2/mcp-oauth"
    }
  }
}

Save the configuration, then complete the browser sign-in from Cursor.

See the OAuth connection guide for more details. For unattended use, configure an API key.

Try it

Search for the latest TypeScript release notes and summarize the sources.

Scrape https://firecrawl.dev and explain what it does.

What you can do

Search

Find current information and read the content of relevant results.

Scrape

Turn URLs into clean markdown or structured data.

Interact

Navigate, click, and fill forms to reach the data you need.

Alexandria

Discover structured data tools, inspect inputs and pricing, then run them through Firecrawl.

Troubleshooting

• Server does not connect: confirm the URL is exactly https://mcp.firecrawl.dev/v2/mcp-oauth and inspect Cursor’s MCP status.
• Sign-in is required or expires: start authentication again from Cursor’s MCP settings.
• Another Firecrawl connection already exists: update the existing server to the OAuth URL and sign in so only one Firecrawl server is active.