All servers / Browser / Selenium MCP server
Selenium MCP server
Selenium WebDriver MCP Server
Tested by ConnectATDScore 75 out of 100. Tested 2026-11-19 on package version 0.2.3. Package: @angiejones/mcp-selenium
Score breakdown
| Runs | 18 / 20 | |
|---|---|---|
| Tool descriptions | 15 / 20 | |
| Package safety | 16 / 20 | |
| Maintenance | 14 / 20 | |
| Adoption | 12 / 20 |
What we saw
- Starts and answers the MCP handshake: yes (5.4 seconds including download)
- Tools offered: 18
- Last published: 2026-02-23
- Weekly downloads (npm): 1,382
- License: ISC · Direct dependencies: 2
Want this server set up for your team?
ConnectATD builds AI automation and wires up MCP servers like this one. Tell us what you are trying to do.
Talk to ConnectATDTools and how they are described
Agents choose tools from these descriptions. Under each name you can see how many of its parameters are explained.
start_browser1 of 2 parameters describedlaunches browser
navigate1 of 1 parameter describednavigates to a URL
interact4 of 4 parameters describedperforms a mouse action on an element
send_keys4 of 4 parameters describedsends keys to an element, aka typing. Clears the field first.
get_element_text3 of 3 parameters describedgets the text content of an element
press_key1 of 1 parameter describedsimulates pressing a keyboard key
upload_file4 of 4 parameters describeduploads a file using a file input element
take_screenshot1 of 1 parameter describedcaptures 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.
close_sessionno parameterscloses the current browser session
get_element_attribute4 of 4 parameters describedgets the value of an attribute on an element. Use this to verify element state. Prefer this over screenshots for validation.
execute_script2 of 2 parameters describedexecutes 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.
window2 of 2 parameters describedmanages browser windows and tabs
frame5 of 5 parameters describedswitches focus to a frame or back to the main page
alert3 of 3 parameters describedhandles a browser alert, confirm, or prompt dialog
add_cookie7 of 7 parameters describedadds a cookie to the current browser session. The browser must be on a page from the cookie's domain before setting it.
get_cookies1 of 1 parameter describedretrieves cookies from the current browser session. Returns all cookies or a specific cookie by name.
delete_cookie1 of 1 parameter describeddeletes cookies from the current browser session. Can delete a specific cookie by name or all cookies.
diagnostics2 of 2 parameters describedretrieves browser diagnostics (console logs, JS errors, or network activity) captured via WebDriver BiDi
Tested in a sandbox with an empty environment: no API keys, a throwaway folder, nothing from a real account. A passing test shows the server runs and responds. It is not a security audit.