The web-browser-mcp-server enables AI assistants to browse and extract content from web pages through the Message Control Protocol (MCP) interface.
Capabilities:
Browse websites: Access and retrieve content from any webpage by providing its URL
Extract content: Capture full webpage content or target specific elements using CSS selectors
Handle complex pages: Process and analyze content from modern, dynamic websites
Structured data extraction: Capture specific data points, metadata, titles, links and sections
Flexible integration: Easily integrate with MCP-enabled systems and workflows
Error handling: Manage request timeouts and handle errors
The server leverages CSS selectors for smart content extraction from web pages, allowing targeted retrieval of specific elements from websites.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@web-browser-mcp-server get the latest headlines from the BBC homepage"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
🌐 Enable AI assistants to browse and extract content from the web through a simple MCP interface.
The Web Browser MCP Server provides AI models with the ability to browse websites, extract content, and understand web pages through the Message Control Protocol (MCP). It enables smart content extraction with CSS selectors and robust error handling.
🤝 Contribute • 📝 Report Bug
Related MCP server: mcp-web-tools
🎯 Smart Content Extraction: Target exactly what you need with CSS selectors
⚡ Lightning Fast: Built with async processing for optimal performance
📊 Rich Metadata: Capture titles, links, and structured content
🛡️ Robust & Reliable: Built-in error handling and timeout management
🌍 Cross-Platform: Works everywhere Python runs
To install Web Browser Server for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install web-browser-mcp-server --client claudeInstall using uv:
uv tool install web-browser-mcp-serverFor development:
# Clone and set up development environment
git clone https://github.com/blazickjp/web-browser-mcp-server.git
cd web-browser-mcp-server
# Create and activate virtual environment
uv venv
source .venv/bin/activate
# Install with test dependencies
uv pip install -e ".[test]"Add this configuration to your MCP client config file:
{
"mcpServers": {
"web-browser-mcp-server": {
"command": "uv",
"args": [
"tool",
"run",
"web-browser-mcp-server"
],
"env": {
"REQUEST_TIMEOUT": "30"
}
}
}
}For Development:
{
"mcpServers": {
"web-browser-mcp-server": {
"command": "uv",
"args": [
"--directory",
"path/to/cloned/web-browser-mcp-server",
"run",
"web-browser-mcp-server"
],
"env": {
"REQUEST_TIMEOUT": "30"
}
}
}
}The server provides a powerful web browsing tool:
Browse and extract content from web pages with optional CSS selectors:
# Basic webpage fetch
result = await call_tool("browse_webpage", {
"url": "https://example.com"
})
# Target specific content with CSS selectors
result = await call_tool("browse_webpage", {
"url": "https://example.com",
"selectors": {
"headlines": "h1, h2",
"main_content": "article.content",
"navigation": "nav a"
}
})Configure through environment variables:
Variable | Purpose | Default |
| Webpage request timeout in seconds | 30 |
Run the test suite:
python -m pytestReleased under the MIT License. See the LICENSE file for details.
Made with ❤️ by the Pear Labs Team
Extract content from a webpage with optional CSS selectors for specific elements
Inputs: url (required), selectors.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 1 tool
With only one tool, there is no possibility of ambiguity or overlap with other tools. The tool's purpose is clearly defined as extracting webpage content with optional element selection.
The single tool name follows a clear verb_noun pattern (browse_webpage). Since there are no other tools to compare against, consistency is inherently perfect.
A single tool for a web browser server is too minimal for the apparent scope. Basic web interactions like navigation, clicking, form filling, or handling multiple tabs are missing, making the server feel incomplete and limiting for agents.
The server is severely incomplete for a web browser domain. It only offers content extraction, lacking essential operations such as navigation, interaction with page elements, or session management, which are critical for typical web automation tasks.
Hosted browser for agents: open pages, search the web, extract data, read PDFs and take screenshots.
Stealth web browser for agents: search, fetch, click, download and type in persistent MCP sessions.
A real browser for your agent: screenshots, page checks, Markdown and PDFs.
Web data for agents. Extract web pages, crawl websites, discover URLs, and search the web.