Fetcher MCP logo

Fetcher MCP

by jae-jae

Fetcher MCP is an MCP server designed to fetch web page content using the Playwright headless browser. It excels at handling dynamic web content and extracting the main content from web pages.

View on GitHub

Last updated: N/A

What is Fetcher MCP?

Fetcher MCP is a server that uses Playwright to fetch web page content, supporting JavaScript execution and intelligent content extraction.

How to use Fetcher MCP?

Run the server using npx -y fetcher-mcp. Install the required browser with npx playwright install chromium. Configure the server in Claude Desktop by adding the appropriate JSON configuration. Use fetch_url to retrieve content from a single URL and fetch_urls for batch retrieval.

Key features of Fetcher MCP

  • JavaScript Support

  • Intelligent Content Extraction

  • Flexible Output Format (HTML and Markdown)

  • Parallel Processing for multiple URLs

Use cases of Fetcher MCP

  • Extracting data from dynamic websites

  • Automating web content retrieval

  • Integrating web content into other applications

  • Batch processing of multiple URLs

FAQ from Fetcher MCP

How do I handle websites with anti-crawler mechanisms?

Use the waitForNavigation: true parameter by including 'Please wait for the page to fully load' in your prompt. You may also need to increase the timeout duration.

How do I preserve the original HTML structure?

Set extractContent: false and returnHtml: true by including 'Please preserve the original HTML content' in your prompt.

How do I fetch the complete page content?

Set extractContent: false by including 'Please fetch the complete webpage content instead of just the main content' in your prompt.

How do I return content as HTML?

Set returnHtml: true by including 'Please return the content in HTML format' in your prompt.

How do I enable debug mode?

Run the server with the --debug option or set debug: true in the request by including 'Please enable debug mode for this fetch operation' in your prompt.