MCP Undetected Chromedriver

Automate Chrome browser control while bypassing anti-bot detection using undetected-chromedriver.

An MCP service built on undetected-chromedriver, providing a comprehensive interface for automating Chrome browser control while bypassing anti-bot detection.

To install MCP-Undetected-Chromedriver for Claude Desktop automatically viaSmithery:

npx -y @smithery/cli install @dragons96/mcp-undetected-chromedriver --client claude

{ "mcpServers": { "mcp-undetected-chromedriver": { "command": "npx", "args": [ "-y", "@smithery/cli@latest", "run", "@dragons96/mcp-undetected-chromedriver", "--config", "{}" ] } } }

# Create virtual environment uv venv # Activate virtual environment # Windows .venv\Scripts\activate # Linux/MacOS source .venv/bin/activate # Install dependencies uv pip install -e .

MCP-Undetected-Chromedriver is an MCP (Multi Channel Protocol) service that wraps the functionality of the undetected-chromedriver library into a series of easy-to-use APIs. This project is particularly suitable for scenarios that require bypassing modern website anti-bot detection mechanisms in automated testing, data scraping, or web automation scripts.

- Based on undetected-chromedriver, effectively bypassing website anti-bot detection
- Provides rich browser operation API interfaces
- Supports screenshots, PDF export, and other functionalities
- Supports complex page interaction operations such as clicking, form filling, dragging, etc.
- Seamlessly integrates with other tools in the MCP ecosystem

- Optimize browser driver management and handle driver interruptions
- Extend API capabilities
- Add more comprehensive error handling and logging
- Improve documentation with more usage examples
- Add support for browser profiles and extensions

The service provides the following main API interfaces:

- browser_navigate: Navigate to a specified URL
- browser_screenshot: Take a screenshot of the current page
- browser_click: Click on page elements
- browser_iframe_click: Click on elements within an iframe
- browser_fill: Fill content in input fields
- browser_select: Select options in dropdown selection boxes
- browser_hover: Hover the mouse over elements
- browser_evalute: Execute JavaScript code
- browser_close: Close the browser
- browser_get_visible_text: Get visible text on the page
- browser_get_visible_html: Get visible HTML on the page
- browser_go_back: Navigate backward in browser history
- browser_go_forward: Navigate forward in browser history
- browser_drag: Drag elements
- browser_press_key: Simulate key presses
- browser_save_as_pdf: Save the page as a PDF

from mcp.client import Client # Create MCP client client = Client() client.start("undetected-chromedriver-mcp-server") # Navigate to website response = client.call("browser_navigate", {"url": "https://example.com"}) print(response) # Take a screenshot response = client.call("browser_screenshot", {"name": "example"}) print(response) # Get page text response = client.call("browser_get_visible_text") print(response.content[0].text) # Close the browser client.call("browser_close")

This service uses the undetected-chromedriver library to create a specialized Chrome browser instance that effectively evades common anti-bot detection mechanisms. The service wraps these features through the MCP protocol, providing an easy-to-use API interface that makes automated testing and web scraping more convenient.

This project is licensed under the MIT License - see theLICENSEfile for details.

A configurable MCP server for browser automation using Puppeteer.