MCP Selenium Server
The MCP Selenium server enables AI agents to automate web browser interactions using Selenium WebDriver, supporting Chrome, Firefox, Edge, and Safari. It provides tools for launching browsers, navigating to URLs, interacting with page elements (clicking, typing, hovering), taking screenshots, and performing other browser automation tasks without requiring manual scripting. This solves the problem of allowing language models to autonomously perform web-based tasks and testing workflows.
- GitHub stars
- 411
- tools
- 18
- last updated
- Mar 5, 2026
Tools
18 toolsPublic tool metadata for what this MCP can expose to an agent.
start_browserLaunches a browser session.
Launches a browser session.
No parameter schema in public metadata yet.
navigateNavigates to a URL.
Navigates to a URL.
No parameter schema in public metadata yet.
interactPerforms a mouse action on an element.
Performs a mouse action on an element.
No parameter schema in public metadata yet.
send_keysTypes text into an element. Clears the field first.
Types text into an element. Clears the field first.
No parameter schema in public metadata yet.
get_element_textGets the text content of an element.
Gets the text content of an element.
No parameter schema in public metadata yet.
get_element_attributeGets an attribute value from an element.
Gets an attribute value from an element.
No parameter schema in public metadata yet.
press_keyPresses a keyboard key.
Presses a keyboard key.
No parameter schema in public metadata yet.
upload_fileUploads a file via a file input element.
Uploads a file via a file input element.
No parameter schema in public metadata yet.
take_screenshotCaptures a screenshot of the current page.
Captures a screenshot of the current page.
No parameter schema in public metadata yet.
close_sessionCloses the current browser session. No parameters.
Closes the current browser session. No parameters.
No parameter schema in public metadata yet.
execute_scriptExecutes JavaScript in the browser. Use for advanced interactions not covered by other tools (e.g., drag and drop, scrolling, reading computed styles, DOM manipulation).
Executes JavaScript in the browser. Use for advanced interactions not covered by other tools (e.g., drag and drop, scrolling, reading computed styles, DOM manipulation).
No parameter schema in public metadata yet.
windowManages browser windows and tabs.
Manages browser windows and tabs.
No parameter schema in public metadata yet.
frameSwitches focus to a frame or back to the main page.
Switches focus to a frame or back to the main page.
No parameter schema in public metadata yet.
alertHandles browser alert, confirm, or prompt dialogs.
Handles browser alert, confirm, or prompt dialogs.
No parameter schema in public metadata yet.
add_cookieAdds a cookie. Browser must be on a page from the cookie's domain.
Adds a cookie. Browser must be on a page from the cookie's domain.
No parameter schema in public metadata yet.
get_cookiesGets cookies. Returns all or a specific one by name.
Gets cookies. Returns all or a specific one by name.
No parameter schema in public metadata yet.
delete_cookieDeletes cookies. Deletes all or a specific one by name.
Deletes cookies. Deletes all or a specific one by name.
No parameter schema in public metadata yet.
diagnosticsGets browser diagnostics captured via WebDriver BiDi (auto-enabled when supported).
Gets browser diagnostics captured via WebDriver BiDi (auto-enabled when supported).
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageReadme
MCP Selenium Server
A Model Context Protocol (MCP) server for Selenium WebDriver — browser automation for AI agents.
Setup
Goose (Desktop)
Paste into your browser address bar:
goose://extension?cmd=npx&arg=-y&arg=%40angiejones%2Fmcp-selenium%40latest&id=selenium-mcp&name=Selenium%20MCP&description=automates%20browser%20interactions
Goose (CLI)
goose session --with-extension "npx -y @angiejones/mcp-selenium@latest"
Claude Code
claude mcp add selenium -- npx -y @angiejones/mcp-selenium@latest
Details
- Repository
- github.com/angiejones/mcp-selenium
- Category
- Web & Browser Automation
Related Web & Browser Automation MCP servers
View all
Parallel Browser MCPetairl/parallel-browser-mcpMCP server for parallel browser automation across multiple providers.51stars
Stealth Agent Browserykshah1309/stealth-agent-browser-mcpStealth Chromium MCP server with hybrid AOM + Set-of-Mark vision and Readability extraction.1stars
Chrome DevToolsbenjaminr/chrome-devtools-mcpAn MCP Server for Chrome DevTools, following the Chrome DevTools Protocol. Integrates with Claude Desktop and Claude Code.297stars