Fetcher: Effortless Content Fetching & Bulletproof Automation

Fetcher: Effortlessly fetch even the trickiest web content with our MCP server powered by Playwright’s headless browser—no fluff, just fast, reliable automation. Your data, delivered.

Visit Repository

✨ Developer Tools

4.2(197 reviews)

295 saves

137 comments

This tool saved users approximately 14954 hours last month!

About Fetcher

What is Fetcher: Effortless Content Fetching & Bulletproof Automation?

Fetcher is a headless browser-powered tool built on Playwright, designed to simplify web content retrieval and automate workflows without breaking a sweat. It intelligently extracts core webpage content, converts it to Markdown, and handles complex JavaScript-rendered sites with reliability.

How to use Fetcher: Effortless Content Fetching & Bulletproof Automation?

Get started instantly with:

npx -y github:jae-jae/fetch-mcp

For troubleshooting, enable visible browser mode:

npx -y github:jae-jae/fetch-mcp --debug

Configure in Claude Desktop by adding MCP server details to your config.json file, specifying the npx command parameters.

Fetcher Features

Key Features of Fetcher: Effortless Content Fetching & Bulletproof Automation?

Smart extraction: Automatically isolates main content areas while ignoring ads/navigation elements
Parallel processing: Batch-process multiple URLs via multi-tab concurrency for speed boosts
Flexible output: Toggle between raw HTML or clean Markdown with adjustable content limits
Timeout controls: Customize navigation wait strategies and page load patience levels

Use cases of Fetcher: Effortless Content Fetching & Bulletproof Automation?

Perfect for:

Aggregating news content from multiple sources into structured documents
Automating product price monitoring across e-commerce platforms
Generating daily content summaries for research workflows
Building headless browser-backed chatbot integrations

Fetcher FAQ

FAQ from Fetcher: Effortless Content Fetching & Bulletproof Automation?

Does it handle dynamic sites? Yes! Built on Playwright's JS rendering capabilities
Can I limit extracted content length? Use maxLength parameter to cap results
How stable is parallel fetching? Failures in one tab won't block others
Can I debug visually? Add --debug flag to inspect browser actions

Content

Fetch MCP

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

Quick Start

Run directly with npx:

npx -y github:jae-jae/fetch-mcp

Debug Mode

Run with the --debug option to show the browser window for debugging:

npx -y github:jae-jae/fetch-mcp --debug

Features

fetch_url - Retrieve web page content from a specified URL
- Uses Playwright headless browser to parse JavaScript
- Supports intelligent extraction of main content and conversion to Markdown
- Supports the following parameters:
  - url: The URL of the web page to fetch (required parameter)
  - timeout: Page loading timeout in milliseconds, default is 30000 (30 seconds)
  - waitUntil: Specifies when navigation is considered complete, options: 'load', 'domcontentloaded', 'networkidle', 'commit', default is 'load'
  - extractContent: Whether to intelligently extract the main content, default is true
  - maxLength: Maximum length of returned content (in characters), default is no limit
  - returnHtml: Whether to return HTML content instead of Markdown, default is false
fetch_urls - Batch retrieve web page content from multiple URLs in parallel
- Uses multi-tab parallel fetching for improved performance
- Returns combined results with clear separation between webpages
- Supports the following parameters:
  - urls: Array of URLs to fetch (required parameter)
  - timeout: Page loading timeout in milliseconds, default is 30000 (30 seconds)
  - waitUntil: Specifies when navigation is considered complete, options: 'load', 'domcontentloaded', 'networkidle', 'commit', default is 'load'
  - extractContent: Whether to intelligently extract the main content, default is true
  - maxLength: Maximum length of returned content (in characters), default is no limit
  - returnHtml: Whether to return HTML content instead of Markdown, default is false

Configuration MCP

Configure this MCP server in Claude Desktop:

On MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json

On Windows: %APPDATA%/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "fetch": {
      "command": "npx",
      "args": ["-y", "github:jae-jae/fetch-mcp"]
    }
  }
}

Development

Install Dependencies

npm install

Install Playwright Browser

Install the browsers needed for Playwright:

npm run install-browser

Build the Server

npm run build

Debugging

Use MCP Inspector for debugging:

npm run inspector

You can also enable visible browser mode for debugging:

node build/index.js --debug