Happy slice of mcp pizzaMCP.pizza
fetcher-mcp

fetcher-mcp

MCP.Pizza Chef: jae-jae

It opens the page in a real but invisible browser first, so news sites, recipes, and other pages that fill themselves in after loading still give up their text. The result comes back as clean reading material with the ads and navigation removed, and it can pull a whole list of links at once. No account or paid key is needed. You do run one command the first time to install the browser it drives.

Web/Research

Use This MCP server To

Read a long article and summarize it in five bullets Pull the text from ten links I paste at once Compare pricing pages from three competitors side by side Grab a recipe without the life story and the ads Save a documentation page as clean text I can reuse

README

Fetcher MCP Icon

中文 | Deutsch | Español | français | 日本語 | 한국어 | Português | Русский

Fetcher MCP

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

🌟 Recommended: OllaMan - Powerful Ollama AI Model Manager.

Advantages

  • JavaScript Support: Unlike traditional web scrapers, Fetcher MCP uses Playwright to execute JavaScript, making it capable of handling dynamic web content and modern web applications.

  • Intelligent Content Extraction: Built-in Readability algorithm automatically extracts the main content from web pages, removing ads, navigation, and other non-essential elements.

  • Flexible Output Format: Supports both HTML and Markdown output formats, making it easy to integrate with various downstream applications.

  • Parallel Processing: The fetch_urls tool enables concurrent fetching of multiple URLs, significantly improving efficiency for batch operations.

  • Resource Optimization: Automatically blocks unnecessary resources (images, stylesheets, fonts, media) to reduce bandwidth usage and improve performance.

  • Robust Error Handling: Comprehensive error handling and logging ensure reliable operation even when dealing with problematic web pages.

  • Configurable Parameters: Fine-grained control over timeouts, content extraction, and output formatting to suit different use cases.

Quick Start

Run directly with npx:

npx -y fetcher-mcp

First time setup - install the required browser by running the following command in your terminal:

npx playwright install chromium

HTTP and SSE Transport

Use the --transport=http parameter to start both Streamable HTTP endpoint and SSE endpoint services simultaneously:

npx -y fetcher-mcp --log --transport=http --host=0.0.0.0 --port=3000

After startup, the server provides the following endpoints:

  • /mcp - Streamable HTTP endpoint (modern MCP protocol)
  • /sse - SSE endpoint (legacy MCP protocol)

fetcher-mcp FAQ

Do I need to pay for anything or get a key?
No. It runs on your own computer and does not rely on a paid service.
Which apps does this work in?
The instructions cover Claude Desktop, and it works in any app where you can add an MCP server.
Can I use this to read a page that takes a moment to load?
Yes. It drives a real browser, so you can tell it to wait for the page to finish filling in.
Will it get past sign-in walls or paywalls?
No. It sees what an ordinary visitor sees, though it can wait longer on pages that run a check before showing content.
How hard is the setup?
You paste a short block into your app's settings and run one command to install the browser it uses.
Can it read several pages at once?
Yes. There is a batch mode that opens multiple links in parallel and returns them together.
Can I get the raw page instead of the cleaned-up version?
Yes. You can ask it to keep the original page untouched when the tidying removes something you wanted.