Selenium MCP
@gaforov
About Selenium MCP
Selenium MCP server for AI agents — 39 browser automation tools with page snapshots, selector hints, multi-session, and batched execution.
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"selenium": {
"command": "npx",
"args": [
"-y",
"@gaforov/selenium-mcp@latest"
]
}
}
}Tools
39Start a Selenium browser session.
Navigate the active browser session to a URL.
Navigate the active browser session to a URL. Alias-friendly alternative to open_url.
Click an element after waiting for it to be visible and enabled.
Perform a mouse action on an element.
Type text into an element after waiting for visibility.
Read visible text from an element.
Read an attribute or property value from an element.
Assert visible element text equals, contains, or matches a regular expression.
Assert an element becomes visible.
Assert an element attribute/property equals, contains, or matches a regular expression.
Wait for an element to exist, with optional visibility requirement.
Wait for an element to be visible.
Find an element and return basic metadata. Alias-friendly discovery tool.
Retry a click for transient UI failures such as stale or intercepted elements.
Press a keyboard key against the active element.
Capture a PNG screenshot and optionally save it to disk.
Return the current browser URL.
Return the current page title.
Return the current page source, optionally truncated for LLM-friendly output.
Capture page structure with stable refs (e1, e2, ...) and reusable selectors for follow-up actions.
Execute synchronous JavaScript in the current page context.
Execute a constrained sequence of browser actions in one call. Supported actions: navigate, wait_for_element, click, type, execute_script.
Send an absolute file path to a file input element.
Manage browser windows and tabs.
Switch browser frame focus by index, name/id, selector, parent, or default content.
Handle browser alert, confirm, or prompt dialogs.
Add a browser cookie for the current page domain.
Get all cookies or one cookie by name.
Delete one cookie by name, or all cookies when name is omitted.
Create a new browser session and select it as active.
Select an existing browser session as active.
List all active browser sessions.
Destroy a specific browser session.
Persist a named selector hint for a domain.
Resolve a selector hint by key and domain.
List selector hints, optionally filtered by domain.
Delete a selector hint by key and domain.
Stop the active Selenium browser session if one exists.
Overview
What is Selenium?
Selenium MCP server for AI agents — 38 browser automation tools with page snapshots, selector hints, multi-session, and batched execution.
How to use Selenium?
The README includes setup instructions such as claude mcp add selenium -- npx -y @gaforov/selenium-mcp@latest.
Key features of Selenium
- Node.js 20+
- Chrome, Firefox, or Edge installed (Selenium Manager provisions the matching driver automatically)
- Selector hints — persist working locators per domain so repeat automations get faster and more reliable over time
- Batched execution — batch_execute runs constrained multi-step sequences in a single tool call, cutting round-trips
- Multi-session — create, select, list, and destroy parallel browser sessions
Use cases of Selenium
- Connect an MCP-compatible client to this repository's service.
- Review the README-backed setup before enabling it in production.
FAQ from Selenium
Where is the source code for Selenium?
The source code is linked from the repository URL on this page.
Does Selenium include a standard MCP config?
If the README contains a parseable MCP configuration block, it is shown in the Config tab.
Frequently asked questions
Where is the source code for Selenium?
The source code is linked from the repository URL on this page.
Does Selenium include a standard MCP config?
If the README contains a parseable MCP configuration block, it is shown in the Config tab.
Basic information
More Browser Automation MCP servers
HTML/CSS to Image
An MCP server for generating images from HTML & CSS or screenshots of URLs using htmlcsstoimage.com.
BitBrowser MCP service
BitBrowser01BitBrowser MCP simple to use, no complicated procedures required. Supports a variety of intelligent agent services.
Parse
Parse.botParse allows your agent to access thousands of APIs instantly. You can use Parse to build an API for any action on any website and edit any previously existing API in our catalogue.
Playwright Mcp
microsoftPlaywright MCP server
Puppeteer MCP Server
merajmehrabiThis MCP server provides browser automation capabilities through Puppeteer, allowing interaction with both new browser instances and existing Chrome windows.
Comments