Fetcher MCP for Cursor: Setup & Config

What you can do with Fetcher in Cursor

Pick it for browser-rendered content extraction with parallel fetching and practical debugging controls.

• Fetch several research URLs in parallel.
• Use a visible browser to log in before retrieving authenticated content.

Before you start: Fetcher in Cursor

• Node.js and npx
• Playwright Chromium
• An MCP-compatible client

The README first installs the browser with npx playwright install chromium. The browser_install tool can also resolve missing-browser errors. An HTTP launch alternative exposes /mcp and /sse. No required environment variables are stated.

Fetcher Cursor configuration

1. Choose Cursor configuration scope

   For Fetcher MCP, open Project: .cursor/mcp.json User: ~/.cursor/mcp.json. Merge into mcpServers at project or user scope.

2. Add Fetcher MCP to Cursor

   Use the fetcher-mcp entry below in mcpServers. Keep Fetcher MCP's documented stdio connection fields and your other Cursor entries.

3. Check Fetcher MCP in Cursor

   Fetcher MCP: Enable in Cursor’s MCP settings; inspect tools.

{
  "mcpServers": {
    "fetcher-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "fetcher-mcp"
      ],
      "env": {}
    }
  }
}

Fetcher tools available to Cursor

Fetcher's stored tool list documents 3 tools; compare it with Cursor's connected tool list, because the stored list is not a live check.

fetch_url

Find fetch_url under Fetcher in Cursor's MCP settings; inspect its arguments when the agent requests a call.

Load one URL in Playwright and return extracted or full page content.

fetch_urls

Find fetch_urls under Fetcher in Cursor's MCP settings; inspect its arguments when the agent requests a call.

browser_install

Find browser_install under Fetcher in Cursor's MCP settings; inspect its arguments when the agent requests a call.

Install Chromium for Playwright, with optional system dependencies or forced reinstallation.

Fetcher: full stored tool descriptions

Troubleshooting Fetcher in Cursor

• Cursor must find npx fetcher-mcp (Node.js/npm) for Fetcher MCP. Enable the project/user entry in MCP settings and inspect its tools.
• Fetcher MCP uses stdio here: Cursor must keep the configured process running; protocol output belongs on stdout and diagnostics on stderr.
• Known limitation: Needs a Playwright Chromium binary and associated runtime dependencies.
• Known limitation: Verification-heavy pages may require manual interaction or timeout tuning.
• Known limitation: Default resource blocking changes what the browser loads.
• General Cursor troubleshooting lives in the /clients/cursor guide.

Frequently asked questions