Fetcher MCP

MCP server for fetch web page content using Playwright headless browser.

Catalog onlyCatalog onlySTDIO

Overview

Fetcher MCP is a server application designed to fetch web page content using the Playwright headless browser, enabling users to retrieve and process web data efficiently.

To use Fetcher MCP, you can run it directly with the command npx -y fetcher-mcp. For debugging, use the --debug option to open the browser window.

fetch_url: Retrieve content from a single URL with intelligent extraction and Markdown conversion. - fetch_urls: Batch fetch content from multiple URLs in parallel for improved performance. - Customizable parameters for timeout, content extraction, and output format.

Scraping data from news websites for analysis.
Collecting product information from e-commerce sites.
Aggregating content from multiple blogs for research purposes.

Add to your AI client

Use these steps to connect Fetcher MCP in Cursor, Claude, VS Code, and other MCP-compatible apps. The same JSON appears in the Use with menu above for one-click copy.

Cursor

Add this to your .cursor/mcp.json file in your project root, then restart Cursor.

.cursor/mcp.json

{
  "mcpServers": {
    "fetcher-mcp-jae-jae": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-fetcher-mcp-jae-jae"
      ]
    }
  }
}

Claude Desktop

Add this server entry to the mcpServers object in your Claude Desktop config, then restart the app.

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

{
  "mcpServers": {
    "fetcher-mcp-jae-jae": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-fetcher-mcp-jae-jae"
      ]
    }
  }
}

Claude Code

Add this to your project's .mcp.json file. Claude Code will detect it automatically.

.mcp.json (project root)

{
  "mcpServers": {
    "fetcher-mcp-jae-jae": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-fetcher-mcp-jae-jae"
      ]
    }
  }
}

VS Code (Copilot)

Add this to your .vscode/mcp.json file. Requires the GitHub Copilot extension with MCP support enabled.

.vscode/mcp.json

{
  "servers": {
    "fetcher-mcp-jae-jae": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-fetcher-mcp-jae-jae"
      ]
    }
  }
}

Windsurf

Add this to your Windsurf MCP config file, then restart Windsurf.

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "fetcher-mcp-jae-jae": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-fetcher-mcp-jae-jae"
      ]
    }
  }
}

Cline

Open Cline settings, navigate to MCP Servers, and add this server configuration.

Cline MCP Settings (via UI)

{
  "mcpServers": {
    "fetcher-mcp-jae-jae": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-fetcher-mcp-jae-jae"
      ]
    }
  }
}

FAQ

Can Fetcher MCP handle JavaScript-heavy websites?

Yes! Fetcher MCP uses Playwright, which can render JavaScript content.

Is there a limit to the number of URLs I can fetch?

No, you can fetch multiple URLs in parallel, but performance may vary based on the number of requests.

How do I configure the MCP server?

You can configure it in the Claude Desktop application by editing the `claude_desktop_config.json` file.

Developer tools