MCP Server Webdriver
UnclaimedMCP Server for browser automation via Selenium WebDriver + geckodriver (Firefox)
Install
mcp-server-webdriver -P workSet up this server
More in Search & Web
Browse the full directoryUnclaimed listing
Is this your MCP server?
This listing was auto-indexed from the public record. Claim it to edit the page, set compatibility and unlock growth tools. Takes under two minutes.
Claim this serverSecurity profile
Claimed and verified servers get a weekly static scan that shows what the code can reach: external services, environment variables, shell commands, agent configuration folders, plus any dependencies with known advisories. Claim this listing to get one. How the security profile works
38 of 38 tools
Documented tools (38)
From project documentation. A server handshake does not verify each tool’s description or behavior.
browser_accept_dialog
Accept a JS alert() / confirm() / prompt()
browser_back
Go back in history
browser_click
Click element (CSS selector)
browser_close
Quit the browser session
browser_dismiss_dialog
Dismiss a JS confirm() / prompt()
browser_execute_js
Run JavaScript — returns JSON
browser_fill
Type text into an input field (clears first by default)
browser_find_elements
List all elements matching a CSS selector
browser_forward
Go forward in history
browser_get_attribute
Value of an HTML attribute on an element (wrapped as untrusted content)
browser_get_cookies
Read all cookies for the current page
browser_get_source
Raw HTML source (wrapped as untrusted content — see Security)
browser_get_text
Visible text (whole page or CSS selector; wrapped as untrusted content)
browser_get_title
Current page <title>
browser_get_url
Current URL
browser_hover
Hover mouse over element (:hover states, tooltips, dropdowns)
browser_navigate
Navigate to a URL (bare hostnames get https://)
browser_open
Open Firefox (URL optional, default about:blank); accepts width, height, useragent for mobile emulation
browser_press_key
Send enter / tab / escape / arrow / F-keys
browser_refresh
Reload the current page
browser_screenshot
Full-page or element PNG screenshot
browser_scroll
Scroll to coords, by offset, or element into view
browser_select
Select <option> in a <select> dropdown
browser_set_cookie
Inject a cookie (auth tokens, session IDs)
browser_set_viewport
Resize the viewport mid-session (e.g. 390×844 for iPhone 14)
browser_status
Session state, geckodriver version, BiDi status, current viewport size, buffer counts
browser_switch_frame
Switch into <iframe> or back to main document
browser_wait
Wait: visible / clickable / present / text:<str>
devtools_clear
Clear buffered DevTools data (use before navigating)
devtools_computed_css
Computed CSS properties of an element
devtools_console
Console output (log / warn / error / info / debug; entries carry an untrusted marker)
devtools_css_variables
CSS custom properties (--var) in scope
devtools_element_info
Bounding box, visibility, attributes, aria, outerHTML
devtools_enable_bidi
Attach BiDi listeners to a running session
devtools_js_errors
JavaScript exceptions only (entries carry an untrusted marker)
devtools_network_all
All network requests (supports limit= and filters)
devtools_network_failed
Failed resources (4xx, 5xx, DNS errors)
devtools_report
Main diagnostic tool — JS errors + console + failed/slow network
Tool change history
FAQ
Questions about MCP Server Webdriver MCP Server
- How do I connect MCP Server Webdriver MCP Server to Claude?
- The listing records `mcp-server-webdriver -P work` as its setup step. Run it, then follow the repository's instructions for the client configuration; the listing names Claude Code, Cursor and Claude Desktop as compatible clients.
- Is MCP Server Webdriver MCP Server free?
- The listed licence is MIT. Check the upstream terms for permitted use and commercial requirements; a public repository does not by itself mean the software is free or open source. Connected APIs and hosted services may have separate charges.
- What can MCP Server Webdriver MCP Server do?
- MCP Server Webdriver MCP Server documents 38 tools to the agent, including browser_accept_dialog, browser_back, browser_click. The descriptions above come from project documentation. A live handshake does not test individual tool behavior.