Fetch MCP: Lightning Speed & Unmatched Reliability

Effortlessly fetch web content with Fetch MCP—powered by Playwright's headless browser magic, built for speed, reliability, and seamless integration!" )

Visit Repository

✨ Developer Tools

4.1(62 reviews)

93 saves

43 comments

Users create an average of 26 projects per month with this tool

About Fetch MCP

What is Fetch MCP: Lightning Speed & Unmatched Reliability?

Fetch MCP is a high-performance server designed to fetch and parse webpage content using the Playwright headless browser. Built for speed and reliability, it intelligently extracts main content and converts it into structured outputs like Markdown or raw HTML. Whether handling single URLs or batch requests, this tool ensures seamless navigation of modern webpages with JavaScript-heavy content.

How to Use Fetch MCP: Lightning Speed & Unmatched Reliability?

Getting started is straightforward. For immediate use, execute the following command in your terminal:

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

When troubleshooting, activate debug mode to visualize browser interactions:

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

Note: Configuration parameters can be fine-tuned based on specific requirements such as timeouts or content extraction preferences.

Fetch MCP Features

Key Features of Fetch MCP: Lightning Speed & Unmatched Reliability?

At its core, Fetch MCP offers two primary functions:

fetch_url: Retrieves content from a single URL with options to control loading behavior (e.g., timeout, waitUntil conditions) and output formatting
fetch_urls: Parallelizes requests across multiple URLs using multi-tab architecture, optimizing throughput without compromising accuracy

Shared capabilities include:

Automatic content extraction using advanced heuristic algorithms
Optional HTML/Markdown output toggles
Granular timeout controls with default 30-second safety nets

Use Cases of Fetch MCP: Lightning Speed & Unmatched Reliability?

Developers leverage this tool in scenarios such as:

Real-time content aggregation for news monitoring systems
SEO audits requiring DOM-based analysis of dynamically rendered pages
Data pipelines needing consistent extraction from complex web structures
Testing environments simulating user interactions at scale

Fetch MCP FAQ

FAQ from Fetch MCP: Lightning Speed & Unmatched Reliability?

Q: How do I configure Fetch MCP in Claude Desktop?
Create or update the configuration file located at:

~/Library/Application Support/Claude/claude_desktop_config.json (MacOS)
%APPDATA%/Claude/claude_desktop_config.json (Windows)

Add this block under "mcpServers":

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

Q: Can I customize browser instances?
Yes. Run npm run install-browser to manage Playwright's underlying browsers, allowing customization of rendering engines and versions as needed.

Q: What guarantees the "unmatched reliability"?
The combination of Playwright's robust engine, configurable timeouts, and smart retries on transient errors ensures stable operations even under adverse network conditions.

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