Selenium Mcp

io.github.pshivaprPublished by GitHub account pshivaprv0.4.6Updated Oct 24, 2026

Selenium Tools for MCP

VerifiedSTDIODesktop onlyWeb Search & Scraping Browser Automation

Server details

Identifier: io.github.pshivapr/selenium-mcp
Transport: STDIO
Runtime: Desktop only
Trust: Verified
Published: Sep 16, 2026

Security note

MCP servers receive tool arguments from a conversation and may perform external actions. Review what a server can do before you enable it, and give it only the access it needs.

The registry verified the GitHub account pshivapr for this listing. That does not show the account is the product's maker.

SourceWeft's checks cover whether the listing is complete and the endpoint answered; they do not review the server's code or what its tools do.

Add a badge to your README

Show readers this MCP server is listed on SourceWeft. The badge links to this page.

[![Listed on SourceWeft](https://sourceweft.com/badge/mcp/io.github.pshivapr%2Fselenium-mcp.svg)](https://sourceweft.com/mcp/io.github.pshivapr%2Fselenium-mcp?utm_source=readme&utm_medium=badge)

Overview

AI-generated overview

A local MCP server that exposes Selenium WebDriver so an assistant can drive real browsers: navigate pages, click and type, manage cookies and windows, and take

What you can do: Open, navigate, refresh, resize and close browser sessions, and read the current URL, title and page source across Chrome, Firefox, Safari and Edge. Find elements and interact with them: click, type, clear, hover, double-click, right-click, drag and drop, upload files, and read text or attributes. Manage cookies and windows, including switching between windows and frames. Run advanced actions such as JavaScript execution, screenshots, dropdown selection, key presses, scrolling and form submission. Check element state (displayed, enabled, selected) and wait for elements or page states.
When to use it: Useful when an assistant should perform real browser automation: end-to-end web testing, form filling, scraping pages that need a live browser, or generating Selenium test code from an observed flow.
Requirements: Runs locally over stdio, typically started with npx from the npm package. Needs Node.js 18 or higher and an installed browser (Chrome, Firefox, Safari or Edge); WebDrivers are managed automatically. The manifest declares an optional API key variable, though the README does not describe using one.

Before you install

The assistant can control a real browser: it can submit forms, click buttons, upload local files and execute arbitrary JavaScript in pages, which may change data or trigger actions on sites you are logged into. Cookie tools can read and modify session cookies, so avoid exposing sensitive accounts. Screenshots and page source may capture private content.

Installation

In SourceWeft

Open Selenium Mcp in the dashboard and add it to a workspace.
Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

[Add to Cursor] [Add to VS Code] [Add to Claude] [Add to ChatGPT] [Add to Codex] [Add to Gemini]

Selenium MCP Server

This is a server implementation that bridges the gap between MCP clients (AI assistants) and Selenium WebDriver. It exposes Selenium WebDriver's functionalities as MCP tools, allowing AI models to utilize them for tasks like:

Browser management (launching, navigating, closing browsers)
Element interaction (clicking, typing, finding elements)
Web scraping and automated testing
Advanced operations like screenshots, cookie management, and JavaScript execution

In essence, the selenium webdriver mcp setup allows AI assistants to leverage the power of Selenium Webdriver for web automation, by communicating with a dedicated Selenium MCP server via the Model Context Protocol. This facilitates tasks such as automated web interactions, testing, and data extraction, all controlled by AI.

[Image]

🚀 Overview

A Model Context Protocol (MCP) server for Selenium that provides comprehensive Selenium WebDriver automation tools for AI assistants and applications. This server enables automated web browser interactions, testing, and scraping through a standardized interface.

Built with TypeScript and modern ES modules, it offers type-safe browser automation capabilities through the Model Context Protocol.

✨ Key Features

Multi-Browser Support: Chrome, Firefox, Safari, and Edge browser automation
Comprehensive Element Interaction: Click, type, hover, drag & drop, file uploads
Advanced Navigation: Forward, backward, refresh, window management
Wait Strategies: Intelligent waiting for elements and page states
Type Safety: Full TypeScript implementation with Zod validation

🤝 Integration

MCP Client Integration

Configure your MCP client to connect to the Selenium server:

Standard Configuration (applicable to Windsurf, Warp, Gemini CLI etc)

json

{  "servers": {    "selenium-mcp": {      "command": "npx",      "args": ["-y", "selenium-webdriver-mcp@latest"]    }  }}

{  "servers": {    "selenium-mcp": {      "command": "npx",      "args": ["-y", "selenium-webdriver-mcp@latest"]    }  }}

Installation in VS Code

Update your mcp.json in VS Code with below configuration

NOTE: If you're new to MCP servers, follow this link Use MCP servers in VS Code

Example 'stdio' type connection

json

{  "servers": {    "selenium-mcp": {      "command": "npx",      "args": [        "-y",        "selenium-webdriver-mcp@latest"      ],      "type": "stdio"    }  },  "inputs": []}

{  "servers": {    "selenium-mcp": {      "command": "npx",      "args": [        "-y",        "selenium-webdriver-mcp@latest"      ],      "type": "stdio"    }  },  "inputs": []}

Example 'http' type connection

json

{  "servers": {    "Selenium": {      "url": "https://smithery.ai/server/@pshivapr/selenium-mcp",      "type": "http"    }  },  "inputs": []}

{  "servers": {    "Selenium": {      "url": "https://smithery.ai/server/@pshivapr/selenium-mcp",      "type": "http"    }  },  "inputs": []}

After installation, the Selenium MCP server will be available for use with your GitHub Copilot agent in VS Code.

To install the Selenium MCP server using the VS Code CLI

bash

# For VS Codecode --add-mcp '{\"name\":\"selenium-mcp\",\"command\": \"npx\",\"args\": [\"selenium-webdriver-mcp@latest\"]}'

# For VS Codecode --add-mcp '{\"name\":\"selenium-mcp\",\"command\": \"npx\",\"args\": [\"selenium-webdriver-mcp@latest\"]}'

bash

# For VS Code Insidersvscode-insiders --add-mcp '{\"name\":\"selenium-mcp\",\"command\": \"npx\",\"args\": [\"selenium-webdriver-mcp@latest\"]}'

# For VS Code Insidersvscode-insiders --add-mcp '{\"name\":\"selenium-mcp\",\"command\": \"npx\",\"args\": [\"selenium-webdriver-mcp@latest\"]}'

To install the package using either npm, or Smithery

Using npm:

Using Smithery

To install Selenium MCP for Claude Desktop automatically via [smithery badge]

Claude Desktop Integration

Add to your Claude Desktop configuration:

json

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

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

Screenshot

[Selenium + Claude]

Prompts

An example prompt to start AI Agent interaction:

Using selenium mcp tools, navigate to <https://parabank.parasoft.com/> click the 'Register' link and signup using dynamic test data and click register. Then generate selenium tests in <YOUR_FAVOURITE_PROGRAMMING_LANGUAGE> using pom, create tests using cucumber features, steps and execute the tests.

Note: For more prompts, look at examples directory of the project

🛠️ MCP Available Tools

Browser Management Tools

Tool	Description	Parameters
`browser_open`	Open a new browser session	`browser`, `options`
`browser_navigate`	Navigate to a URL	`url`
`browser_navigate_back`	Navigate back in history	None
`browser_navigate_forward`	Navigate forward in history	None
`browser_title`	Get the current page title	None
`browser_refresh`	Refresh the current page	None
`browser_get_url`	Get the current page URL	None
`browser_get_page_source`	Get the current page HTML source	None
`browser_maximize`	Maximize the browser window	None
`browser_resize`	Resize browser window	`width`, `height`
`browser_close`	Close current browser session	None

Cookie Management Tools

Tool	Description	Parameters
`browser_get_cookies`	Get all cookies from the current browser session	None
`browser_get_cookie_by_name`	Get a specific cookie by name	`cookie` (cookie name)
`browser_add_cookie_by_name`	Add a new cookie to the browser	`cookie` (cookie name), `value`
`browser_set_cookie_object`	Set a cookie object in the browser	`cookie` (cookie object as string)
`browser_delete_cookie`	Delete a specific cookie by name	`value` (cookie name to delete)
`browser_delete_cookies`	Delete all cookies from the current browser session	None

Window Management Tools

Tool	Description	Parameters
`browser_switch_to_window`	Switch to a different browser window by handle	`windowHandle`
`browser_switch_to_original_window`	Switch back to the original browser window	None
`browser_switch_to_window_by_title`	Switch to a window by its page title	`title`
`browser_switch_window_by_index`	Switch to a window by its index position	`index`
`browser_switch_to_window_by_url`	Switch to a window by its URL	`url`

Element Interaction Tools

Tool	Description	Parameters
`browser_find_element`	Find an element on the page	`by`, `value`, `timeout`
`browser_find_elements`	Find multiple elements on the page	`by`, `value`, `timeout`
`browser_click`	Click on an element	`by`, `value`, `timeout`
`browser_type`	Type text into an element	`by`, `value`, `text`, `timeout`
`browser_get_element_text`	Get text content of element	`by`, `value`, `timeout`
`browser_file_upload`	Upload file via input element	`by`, `value`, `filePath`, `timeout`
`browser_clear`	Clear text from an element	`by`, `value`, `timeout`
`browser_get_attribute`	Get element attribute value	`by`, `value`, `attribute`, `timeout`

Element State Validation Tools

Tool	Description	Parameters
`browser_element_is_displayed`	Check if an element is visible on the page	`by`, `value`, `timeout`
`browser_element_is_enabled`	Check if an element is enabled for interaction	`by`, `value`, `timeout`
`browser_element_is_selected`	Check if an element is selected (checkboxes, radio buttons)	`by`, `value`, `timeout`

Frame Management Tools

Tool	Description	Parameters
`browser_switch_to_frame`	Switch to an iframe element	`by`, `value`, `timeout`
`browser_switch_to_parent_frame`	Switch to the parent frame (from nested iframe)	None
`browser_switch_to_default_content`	Switch back to the main page content	None

Advanced Action Tools

Tool	Description	Parameters
`browser_hover`	Hover over an element	`by`, `value`, `timeout`
`browser_double_click`	Double-click on an element	`by`, `value`, `timeout`
`browser_right_click`	Right-click (context menu)	`by`, `value`, `timeout`
`browser_drag_and_drop`	Drag from source to target	`by`, `value`, `targetBy`, `targetValue`, `timeout`
`browser_wait_for_element`	Wait for element to appear	`by`, `value`, `timeout`
`browser_execute_script`	Execute JavaScript code	`script`, `args`
`browser_screenshot`	Take a screenshot	`filename` (optional)
`browser_select_dropdown_by_text`	Select dropdown option by visible text	`by`, `value`, `text`, `timeout`
`browser_select_dropdown_by_value`	Select dropdown option by value	`by`, `value`, `dropdownValue`, `timeout`
`browser_key_press`	Press a keyboard key in the browser	`key`, `timeout`

Scrolling Tools

Tool	Description	Parameters
`browser_scroll_to_element`	Scroll to bring an element into view	`by`, `value`, `timeout`
`browser_scroll_to_top`	Scroll to the top of the page	None
`browser_scroll_to_bottom`	Scroll to the bottom of the page	None
`browser_scroll_to_coordinates`	Scroll to specific coordinates	`x`, `y`
`browser_scroll_by_pixels`	Scroll by specified number of pixels	`x`, `y`

Form Interaction Tools

Tool	Description	Parameters
`browser_select_checkbox`	Select/check a checkbox	`by`, `value`, `timeout`
`browser_unselect_checkbox`	Unselect/uncheck a checkbox	`by`, `value`, `timeout`
`browser_submit_form`	Submit a form element	`by`, `value`, `timeout`
`browser_focus_element`	Focus on a specific element	`by`, `value`, `timeout`
`browser_blur_element`	Remove focus from a specific element	`by`, `value`, `timeout`

Element Locator Strategies

id: Find by element ID
css: Find by CSS selector
xpath: Find by XPath expression
name: Find by name attribute
tag: Find by HTML tag name
class: Find by CSS class name

📋 Requirements

Node.js: Version 18.0.0 or higher
Browsers: Chrome, Firefox, Safari, or Edge installed
WebDrivers: Automatically managed by selenium-webdriver
Operating System: Windows, macOS, or Linux

🚦 Development

Getting Started

Clone the repository

Install dependencies

Build the project

Running the Server

Production Mode

Development Mode (with auto-reload)

Direct Execution

Using as CLI Tool

After building, you can use the server as a global command:

📝 License

MIT License - see LICENSE file for details.

🤝 Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

Fork the repository
Create your feature branch (git checkout -b feature/AmazingFeature)
Commit your changes (git commit -m 'Add some AmazingFeature')
Push to the branch (git push origin feature/AmazingFeature)
Open a Pull Request

Badges/Mentions

MCP Market

Pulse

[MCP Badge]

Built with ❤️ for the Model Context Protocol ecosystem

Source: README.md at commit bc06d84

Tools

SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

v0.4.6LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

Reached in the last 30 days25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
Auth declared10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
DescriptionRequired15 pts
Logo10 pts
Documentation15 pts
License10 pts