What is Mcp Web Tools

MCP Web Tools is a powerful MCP server designed to provide web access for LLMs, enhancing the capabilities of traditional methods for searching, fetching, and extracting content from the web.

Use cases

Use cases include extracting data from websites for analysis, fetching content for educational purposes, generating formatted reports from web data, and enhancing LLM capabilities with real-time web information.

How to use

To use MCP Web Tools, install it via Claude Desktop or Claude Code. You can add it to your setup with the command ‘claude mcp add web-tools uvx mcp-web-tools’. Optionally, you can include a Brave Search API key for improved search results.

Key features

Key features include: good search results without requiring an API key, sophisticated fetching for complex JavaScript sites, content extraction in well-formatted Markdown, support for PDFs, image loading and display, and options for advanced use cases like loading raw HTML.

Where to use

MCP Web Tools can be used in various fields such as web development, data extraction, content creation, and research, where access to web content is essential.

MCP Web Tools

This package provides a powerful MCP server to equip LLMs with web access, going beyond naive methods of searching, fetching and extracting content.

Introduction

I created this package out of the frustration that most MCP servers enabling web access to LLMs, didn’t perform as well as I hoped. Some of these shortcomings I wanted fix, include:

• [x] Good search results without requiring an API key
• [x] Sophisticated fetching for more complex JavaScript sites
• [x] Extracting content in nicely formatted Markdown
• [x] Support for extracting content from PDFs
• [x] Support for loading and displaying images
• [x] Usage options for advanced cases like loading raw HTML

Installation

Claude Desktop

Claude Code

claude mcp add web-tools uvx mcp-web-tools

Or to also set the Brave Search API key:

claude mcp add web-tools uvx mcp-web-tools -e BRAVE_SEARCH_API_KEY=<key>

Internals

The package is written in Python using powerful libraries and services under the hood to improve results.

Searching

We use the Brave Search API if an API key is provided with fallbacks a scraped Google workaround and finally DuckDuckGO if everything else fails. While we’d recommend getting a free Brave API key, the fallbacks should work more than well enough for most use cases and work loads.

Fetching

The fetching of web content is based on Zendriver, a fork of nodriver for next level webscraping and performance. It should stay undetected for most anti-bot solutions and fetch content even from complex JS-based sites.

Extracting

For web extraction, we use Trafilatura which consistently outperforms other alternatives for extracting content from HTML pages. For PDFs, we use PyMuPDF4LLM which similarly extracts content in an easy-to-read format for LLMs, with advanced layout support.

Contributing

While it’s impossible to support all pages and layouts, we thrive to make this package better over time. For unsupported sites, problems, or feature requests open an issue.