Selenium

Recommended

by angiejones

108 6.1k downloads Not rated yet MIT

GitHub

About

Automates web browser actions with Selenium WebDriver.

Details

Repository: angiejones/mcp-selenium
License: MIT

Explore

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

Download and install Highlight from highlightai.com/download
Navigate to the plugins tab and select "Add Custom Plugin"
Configure the plugin with the settings below
Plugin Name Selenium

Command (node, npx, python, etc.) npx
Arguments
- Argument 1 -y
- Argument 2 @angiejones/mcp-selenium@latest
Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
Enable "Start Automatically" if you want the plugin to start when Highlight launches

Setting up with Cursor

Open Cursor's settings
Navigate to the MCP section
Click "Add new Global MCP server"
Copy and paste the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "selenium": {
            "env": {},
            "args": [
                "-y",
                "@angiejones/mcp-selenium@latest"
            ],
            "shell": false,
            "command": "npx"
        }
    }
}

JSON

{
    "mcpServers": {
        "selenium": {
            "env": {},
            "args": [
                "/c",
                "npx",
                "-y",
                "@angiejones/mcp-selenium@latest"
            ],
            "shell": true,
            "command": "cmd"
        }
    }
}

JSON

{
    "mcpServers": {
        "selenium": {
            "env": {},
            "args": [
                "-y",
                "@angiejones/mcp-selenium@latest"
            ],
            "shell": false,
            "command": "npx"
        }
    }
}

Setting up with Claude Desktop

Open Claude Desktop's settings
Go to the Integrations tab
Click "Add MCP Server"
Use the configuration below based on your operating system

Note: Make sure Claude Desktop is running before attempting to connect.

JSON

{
    "mcpServers": {
        "selenium": {
            "env": {},
            "args": [
                "-y",
                "@angiejones/mcp-selenium@latest"
            ],
            "shell": false,
            "command": "npx"
        }
    }
}

JSON

{
    "mcpServers": {
        "selenium": {
            "env": {},
            "args": [
                "/c",
                "npx",
                "-y",
                "@angiejones/mcp-selenium@latest"
            ],
            "shell": true,
            "command": "cmd"
        }
    }
}

JSON

{
    "mcpServers": {
        "selenium": {
            "env": {},
            "args": [
                "-y",
                "@angiejones/mcp-selenium@latest"
            ],
            "shell": false,
            "command": "npx"
        }
    }
}

Setting up with Windsurf

Open Windsurf's preferences
Go to the Integrations section
Click "Add MCP Integration"
Use the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "selenium": {
            "env": {},
            "args": [
                "-y",
                "@angiejones/mcp-selenium@latest"
            ],
            "shell": false,
            "command": "npx"
        }
    }
}

JSON

{
    "mcpServers": {
        "selenium": {
            "env": {},
            "args": [
                "/c",
                "npx",
                "-y",
                "@angiejones/mcp-selenium@latest"
            ],
            "shell": true,
            "command": "cmd"
        }
    }
}

JSON

{
    "mcpServers": {
        "selenium": {
            "env": {},
            "args": [
                "-y",
                "@angiejones/mcp-selenium@latest"
            ],
            "shell": false,
            "command": "npx"
        }
    }
}

Setting up with Cline

Open Cline's settings
Navigate to the Integrations section
Click "Add MCP Server"
Copy and paste the configuration below based on your operating system

Note: Make sure to restart Cline after adding the configuration.

JSON

{
    "mcpServers": {
        "selenium": {
            "env": {},
            "args": [
                "-y",
                "@angiejones/mcp-selenium@latest"
            ],
            "shell": false,
            "command": "npx"
        }
    }
}

JSON

{
    "mcpServers": {
        "selenium": {
            "env": {},
            "args": [
                "/c",
                "npx",
                "-y",
                "@angiejones/mcp-selenium@latest"
            ],
            "shell": true,
            "command": "cmd"
        }
    }
}

JSON

{
    "mcpServers": {
        "selenium": {
            "env": {},
            "args": [
                "-y",
                "@angiejones/mcp-selenium@latest"
            ],
            "shell": false,
            "command": "npx"
        }
    }
}

Setting up with Goose

Open Goose's preferences
Go to the Integrations tab
Select "MCP Servers"
Click "Add New Server"
Use the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "selenium": {
            "env": {},
            "args": [
                "-y",
                "@angiejones/mcp-selenium@latest"
            ],
            "shell": false,
            "command": "npx"
        }
    }
}

JSON

{
    "mcpServers": {
        "selenium": {
            "env": {},
            "args": [
                "/c",
                "npx",
                "-y",
                "@angiejones/mcp-selenium@latest"
            ],
            "shell": true,
            "command": "cmd"
        }
    }
}

JSON

{
    "mcpServers": {
        "selenium": {
            "env": {},
            "args": [
                "-y",
                "@angiejones/mcp-selenium@latest"
            ],
            "shell": false,
            "command": "npx"
        }
    }
}

From the repository

<details open>
<summary><strong>Goose (Desktop)</strong></summary>

Paste into your browser address bar:
```

`start_browser`

Launches a browser session. Parameters: browser (string, required), options (object, optional)

`navigate`

Navigates to a URL. Parameters: url (string, required)

`interact`

Performs a mouse action on an element. Parameters: action (string, required), by (string, required), value (string, required), timeout (number, optional)

`send_keys`

Types text into an element. Clears the field first. Parameters: by (string, required), value (string, required), text (string, required), timeout (number, optional)

`get_element_text`

Gets the text content of an element. Parameters: by (string, required), value (string, required), timeout (number, optional)

`get_element_attribute`

Gets an attribute value from an element. Parameters: by (string, required), value (string, required), attribute (string, required), timeout (number, optional)

`press_key`

Presses a keyboard key. Parameters: key (string, required)

`upload_file`

Uploads a file via a file input element. Parameters: by (string, required), value (string, required), filePath (string, required), timeout (number, optional)

`take_screenshot`

Captures a screenshot of the current page. Parameters: outputPath (string, optional)

`close_session`

Closes the current browser session. No parameters.

`execute_script`

Executes JavaScript in the browser. Use for advanced interactions not covered by other tools. Parameters: script (string, required), args (array, optional)

`window`

Manages browser windows and tabs. Parameters: action (string, required), handle (string, optional)

`frame`

Switches focus to a frame or back to the main page. Parameters: action (string, required), by (string, optional), value (string, optional), index (number, optional), timeout (number, optional)

`alert`

Handles browser alert, confirm, or prompt dialogs. Parameters: action (string, required), text (string, optional), timeout (number, optional)

`add_cookie`

Adds a cookie. Browser must be on a page from the cookie's domain. Parameters: name (string, required), value (string, required), domain (string, optional), path (string, optional), secure (boolean, optional), httpOnly (boolean, optional), expiry (number, optional)

`get_cookies`

Gets cookies. Returns all or a specific one by name. Parameters: name (string, optional)

`delete_cookie`

Deletes cookies. Deletes all or a specific one by name. Parameters: name (string, optional)

`diagnostics`

Gets browser diagnostics captured via WebDriver BiDi. Parameters: type (string, required), clear (boolean, optional)

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "selenium": {
            "env": {},
            "args": [
                "-y",
                "@angiejones/mcp-selenium@latest"
            ],
            "shell": false,
            "command": "npx"
        }
    }
}

Linux

{
    "env": [],
    "args": [
        "-y",
        "@angiejones/mcp-selenium@latest"
    ],
    "shell": false,
    "command": "npx"
}

Macos

{
    "env": [],
    "args": [
        "-y",
        "@angiejones/mcp-selenium@latest"
    ],
    "shell": false,
    "command": "npx"
}

Windows

{
    "env": [],
    "args": [
        "/c",
        "npx",
        "-y",
        "@angiejones/mcp-selenium@latest"
    ],
    "shell": true,
    "command": "cmd"
}

A Model Context Protocol (MCP) server for Selenium WebDriver — browser automation for AI agents.

goose://extension?cmd=npx&arg=-y&arg=%40angiejones%2Fmcp-selenium%40latest&id=selenium-mcp&name=Selenium%20MCP&description=automates%20browser%20interactions

goose session --with-extension "npx -y @angiejones/mcp-selenium@latest"

claude mcp add selenium -- npx -y @angiejones/mcp-selenium@latest

{ "mcpServers": { "selenium": { "command": "npx", "args": ["-y", "@angiejones/mcp-selenium@latest"] } } }

Open Chrome, go to github.com/angiejones, and take a screenshot.

The agent will call Selenium's APIs tostart_browser,navigate, andtake_screenshot. No manual scripting or explicit directions needed.

Safari note:Requires macOS. Runsudo safaridriver --enableonce and enable "Allow Remote Automation" in Safari → Settings → Developer. No headless mode.

Types text into an element. Clears the field first.

Gets an attribute value from an element.

Uploads a file via a file input element.

Captures a screenshot of the current page.

Closes the current browser session. No parameters.

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).

Switches focus to a frame or back to the main page.

Handles browser alert, confirm, or prompt dialogs.

Gets browser diagnostics captured via WebDriver BiDi (auto-enabled when supported).

MCP resources provide read-only data that clients can access without calling a tool.

Returns the current browser session status (active session ID or "no active session").

Returns an accessibility tree snapshot of the current page — a compact, structured JSON representation of interactive elements and text content. Much smaller than full HTML. Useful for understanding page layout and finding elements to interact with.

git clone https://github.com/angiejones/mcp-selenium.git cd mcp-selenium npm install

Requires Chrome + chromedriver on PATH. Tests run headless.

npx -y @smithery/cli install @angiejones/mcp-selenium --client claude

npm install -g @angiejones/mcp-selenium mcp-selenium

This is a web browser that enables your coding agent, such as Claude Code, to visit websites on your behalf and assist you in identifying bugs or creating UI test cases.

Control your real Chrome from Claude Code. 29 tools including CAPTCHA solving, file upload, multi-session, and human-in-the-loop.

MCP tools for crawler-readability and discovery-file diagnostics, including crawler-visible HTML inspection, raw-vs-rendered comparison, and discovery-file checks.

Selenium MCP server for AI agents — 39 browser automation tools with page snapshots, selector hints, multi-session, and batched execution.

Automated QA testing for websites to find UI bugs, broken links, and accessibility issues.

Official Playwright MCP server for browser automation, page inspection, screenshots, and web interaction from Claude, Cursor, and other AI agents.

Render website screenshots with ScreenshotOne

Attaches to existing browser sessions using the Chrome DevTools Protocol for automation and interaction.

Help your AI agent finish more browser tasks.

Automate remote browsers using the BrowserCat API.

No reviews yet — be the first

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.

About

Details

Explore

Setting up with Highlight

From the repository

start_browser

navigate

interact

send_keys

get_element_text

get_element_attribute

press_key

upload_file

take_screenshot

close_session

execute_script

window

frame

alert

add_cookie

get_cookies

delete_cookie

diagnostics

Claude Desktop / Cursor

Linux

Macos

Windows

Videos about Selenium

Selenium MCP Server with Claude AI | Automation Testing Tutorial

AI Writes Selenium Tests in IntelliJ IDEA — Selenium Boot MCP Plugin (Live Demo)

Selenium MCP Server Explained | IntelliJ + GitHub Copilot Automation

More like this

@mendableai/firecrawl Mcp Server

Playwright

Sentry

Github

`start_browser`

`navigate`

`interact`

`send_keys`

`get_element_text`

`get_element_attribute`

`press_key`

`upload_file`

`take_screenshot`

`close_session`

`execute_script`

`window`

`frame`

`alert`

`add_cookie`

`get_cookies`

`delete_cookie`

`diagnostics`