add_cookie
adds a cookie to the current browser session. The browser must be on a page from the cookie's domain before setting it.
LABSCO SUMMARY
A failing step comes back as an attribute value and a console error, not as a picture to squint at.
The tool descriptions steer away from screenshots on purpose: get_element_attribute and execute_script are named as the way to verify state, the accessibility://current resource as the way to understand page content, and take_screenshot is reserved for questions about layout and styling. diagnostics then supplies what a screenshot never could — the JavaScript error and the network activity behind the failure — in the same session that produced it. That combination makes it usable for reproducing a bug report, not only for scripted clicking.
What it is
A Selenium WebDriver session exposed as 18 tools: browser lifecycle, element interaction by locator, state readback, and browser-level diagnostics captured over WebDriver BiDi.
What you get
- A browser session you start with your choice of browser and options, and close when finished
- Element interaction by locator with a timeout: mouse actions, typing that clears the field first, keyboard key presses, and file upload through a file input
- State readback for assertions — an element's text, an element's attribute, or arbitrary JavaScript that can batch several reads into one call
- Console logs, JavaScript errors and network activity captured over WebDriver BiDi, retrieved as a group and clearable
- The awkward parts of real pages: window and tab management, switching into a frame and back, and dismissing an alert, confirm or prompt dialog
- Cookie control on the live session — add one for the current domain, read all or one by name, delete one or all
- Screenshots to a path when the question is visual layout or styling
Requirements
A browser on the machine for Selenium to drive, chosen at the time you start the session. No credentials and no account. MIT licensed.
Setup effort
One command — npx -y @angiejones/mcp-selenium@latest
USE CASES
01
Reproducing a bug report step by step
Open the browser the reporter used, walk the same path — navigate, click, type — and stop where they stopped. Typing clears the field first, so a rerun does not append to what the last attempt left behind.
02
Checking a form submits what you think it submits
Read the values back off the elements rather than looking at a picture of them. One script call can collect several element states at once, which is quicker than an attribute call per field.
03
Testing a page as an already signed-in user
Set the session cookie on the current domain and skip the login form entirely, then clear it to check what a signed-out visitor sees on the same page.
04
Explaining why a step failed rather than just that it did
Pull the console logs, JavaScript errors or network activity captured over WebDriver BiDi for the moment it broke, and take a screenshot only when the question turns out to be visual after all.
05
Handling flows that leave the main page
Payment iframes, pop-out windows and confirm dialogs are where scripted runs usually stop. Switching frames, moving between windows and answering a dialog are each a call rather than a workaround.
18 tools
Counted once with only startup setup. Other versions, modes or optional credentials may expose a different list.
alert
handles a browser alert, confirm, or prompt dialog
close_session
closes the current browser session
delete_cookie
deletes cookies from the current browser session. Can delete a specific cookie by name or all cookies.
diagnostics
retrieves browser diagnostics (console logs, JS errors, or network activity) captured via WebDriver BiDi
execute_script
executes JavaScript in the browser and returns the result. Use for advanced interactions not covered by other tools (e.g., drag and drop, scrolling, reading computed styles, manipulating the DOM directly). Also useful for batch-reading multiple element values/states in a single call instead of multiple get_element_attribute calls.
frame
switches focus to a frame or back to the main page
get_cookies
retrieves cookies from the current browser session. Returns all cookies or a specific cookie by name.
get_element_attribute
gets the value of an attribute on an element. Use this to verify element state. Prefer this over screenshots for validation.
get_element_text
gets the text content of an element
interact
performs a mouse action on an element
navigate
navigates to a URL
press_key
simulates pressing a keyboard key
send_keys
sends keys to an element, aka typing. Clears the field first.
start_browser
launches browser
take_screenshot
captures a screenshot of the current page. Prefer using the accessibility://current resource for understanding page content. Use get_element_text, get_element_attribute, or execute_script to verify element state. Only use screenshots when visual layout or styling needs to be verified.
upload_file
uploads a file using a file input element
window
manages browser windows and tabs
BEFORE YOU INSTALL
What to know first
Tools you get
18 tools when we connected.
Requires
npx on PATH
CONTEXT COST
Light Standing cost
Rated by the size of the 18 tool definitions that ride along on every turn, not by how many there are
INSTALLATION
Connect your client
Add the block to your client, or run the command directly.
Server setup
Configuration file
JSON
{
"mcpServers": {
"mcp-selenium": {
"command": "npx",
"args": [
"-y",
"@angiejones/mcp-selenium@latest"
]
}
}
}npx
TERMINAL
npx -y @angiejones/mcp-selenium@latest
