Web Browser

Provides web browsing capabilities for AI apps, extracting content with CSS selectors and returning structured metadata.

python

GitHub Stars

python

Language

7 months ago

First Indexed

3 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "mcp-mirror-blazickjp_web-browser-mcp-server": {
      "command": "uv",
      "args": [
        "--directory",
        "/path/to/web-browser-mcp-server",
        "run",
        "web-browser-mcp-server"
      ],
      "env": {
        "LOG_LEVEL": "info",
        "USER_AGENT": "Mozilla/5.0 (compatible; MSIE 10.0; Windows NT 6.1; Trident/6.0)",
        "MAX_RETRIES": "3",
        "REQUEST_TIMEOUT": "30"
      }
    }
  }
}

You can empower your AI applications with built-in web browsing capabilities. This MCP Server lets you read, extract, and structure data from web pages, enabling precise content targeting and fast, reliable results through asynchronous processing.

How to use

You integrate the server with an MCP client to fetch web content and extract exactly what you need. Use the provided functions to request a page and apply CSS selectors to pull specific parts like headlines, article bodies, or navigation links. The server returns structured results with titles, links, and content metadata, making it easy to feed into your AI workflow.

Typical usage patterns include fetching a page and then targeting sections with selectors. For example, retrieve a page and extract headlines, article content, and navigation links, all in one call.

How to install

Prerequisites you need before starting:

Python is installed on your system
A Python package manager is available (pip)
You have a tool to run MCP servers (UVX/uv) installed or available in PATH

Install the MCP server package using your preferred method:

# Using pip
pip install web-browser-mcp-server

# Using uv (recommended)
uv pip install web-browser-mcp-server

MCP server configuration for local use

Configure a local MCP server instance to run with UVX, pointing to your installation directory and exposing the server under a visible name.

{
  "mcpServers": {
    "web-browser-mcp-server": {
      "command": "uv",
      "args": [
        "--directory",
        "/path/to/web-browser-mcp-server",
        "run",
        "web-browser-mcp-server"
      ],
      "env": {
        "REQUEST_TIMEOUT": "30"
      }
    }
  }
}

Available tools

browse_webpage

Fetch a webpage and optionally apply CSS selectors to extract structured content such as headlines, main content, and navigation links.

Built by

VeilStrat

AI signals for GTM teams