SeleniumBase MCP
OfficialRelated Servers
Alternatives to SeleniumBase MCP
AlicenseAqualityAmaintenanceEnables MCP clients like Claude Desktop and Claude Code to drive a real browser with SeleniumBase automation. Offers three variants: WebDriver-based general automation, Pure CDP Mode for bot-detection bypass, and a broad SB() API with MFA and downloads.824425 PyPI9MIT
Related Servers
- AlicenseAqualityDmaintenanceStealth browser automation for AI agents, using source-patched Chromium to bypass bot detection systems like Cloudflare, reCAPTCHA, and FingerprintJS.28Apache 2.0
- AlicenseNot gradedqualityDmaintenanceProvides browser automation with enhanced anti-detection using undetected-chromedriver, enabling robust web scraping and interaction with sites that employ bot protection measures. It is fully compatible with server-puppeteer and includes network traffic monitoring capabilities.1MIT
- AlicenseAqualityCmaintenanceOpen-source browser automation API with anti-detection for AI agents, web scraping, and automation, providing undetectable Chrome via MCP and REST API with Cloudflare bypass.2410MIT
- AlicenseAqualityDmaintenanceEnables browser automation with anti-detection features, including navigation, interaction, form filling, and session management.2210MIT
- AlicenseAqualityDmaintenanceAn MCP service that automates Chrome browser control while bypassing anti-bot detection mechanisms, enabling web scraping, testing and automation on sites with sophisticated bot protection.1611MIT
- AlicenseNot gradedqualityBmaintenanceAn MCP server for stealth browser automation that uses human-like interaction patterns to bypass bot detection via the Chrome DevTools Protocol. It enables users to navigate, interact with elements, and capture data from websites using undetectable behaviors like Bezier mouse movements and Gaussian typing delays.117 npm1MIT
TDQS
Scored across 24 tools
Each tool targets a clearly distinct browser automation concern, and the condition-related tools (check_if_condition, wait_for_condition, assert_condition) are explicitly differentiated by their semantics. Read-style tools like get_content, find_elements, and get_attributes also have clear boundaries despite touching similar page data.
Tool names overwhelmingly follow a consistent snake_case imperative verb_noun pattern, with useful groups like get_*, manage_*, and *_condition. Minor deviations like hover_action and check_if_condition are still readable and do not create real confusion.
At 24 tools, the server is on the heavier side, but the count is justified by the breadth of browser automation: lifecycle, navigation, content extraction, interaction, state checking, tabs, windows, storage, cookies, and JavaScript execution. It is slightly over the ideal compact range but not bloated.
The surface covers the core browser automation lifecycle well: launch/close, navigation, reading content, interacting with elements, waiting/asserting, managing tabs/windows/cookies/storage, and saving page artifacts. Notable gaps like file upload handling and native alert/dialog interaction are absent but can often be worked around via run_javascript or other primitives.