Selenium MCP Server
Enable AI assistants and applications to perform automated web browser interactions, testing, and scraping through a standardized interface.
What it can do
- Browser Open: Open a new browser session
- Browser Navigate: Navigate to a URL
- Browser Navigate Back: Navigate back in the browser
What data it sees
Do you need an account
No: the server works without sign-in
Enable AI assistants and applications to perform automated web browser interactions, testing, and scraping through a standardized interface. Control multiple browsers with comprehensive element interaction and advanced navigation tools. Benefit from type-safe, robust browser automation powered by Selenium WebDriver.
How to connect
How to connect Selenium MCP Server to Claude
The server address to paste into Claude settings:
https://selenium-mcp--pshivapr.run.tools
- Open Claude (claude.ai or the desktop app).
- Go to Settings → Connectors.
- Click Add custom connector.
- Paste the server address copied below into Remote MCP server URL and click Add.
- In a chat, click + → Connectors and switch the new connector on.
Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.
Authorization
After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.
How to connect Selenium MCP Server to ChatGPT
The server address to paste into ChatGPT settings:
https://selenium-mcp--pshivapr.run.tools
- Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
- Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
- Open Settings → Connectors and click Create.
- Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
- Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
- In a new chat open + → Apps/Connectors and enable the connector.
OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.
Authorization
On first use ChatGPT opens the service's sign-in window. Sign in and approve access.
How to connect Selenium MCP Server to Cursor
The server address to paste into Cursor settings:
https://selenium-mcp--pshivapr.run.tools
Fastest: click Open in Cursor below and confirm the prompt.
Manually:
- In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
- Paste the JSON copied below into
~/.cursor/mcp.json(per project:.cursor/mcp.jsonin the repo root). - Save the file. The server appears in the MCP list; authorize it there if asked.
Authorization
If the service needs sign-in, an authorize button appears next to the server in the MCP list.
Server tool list (56)
Raw names from tools/list. Only developers need these.
| browser_open | Open a new browser session |
| browser_navigate | Navigate to a URL |
| browser_navigate_back | Navigate back in the browser |
| browser_navigate_forward | Navigate forward in the browser |
| browser_title | Get the current page title |
| browser_get_url | Get the current page URL |
| browser_get_page_source | Get the current page source |
| browser_maximize | Maximize the browser window |
| browser_resize | Resize the browser window |
| browser_refresh | Refresh the current page |
| browser_switch_to_window | Switch to a different browser window |
| browser_switch_to_original_window | Switches back to the original browser window |
| browser_switch_to_window_by_title | Switch to a window by its title |
| browser_switch_window_by_index | Switch to a window by its index |
| browser_switch_to_window_by_url | Switch to a window by its URL |
| browser_close | Close the current browser session |
| browser_find_element | Find an element |
| browser_find_elements | Find multiple elements |
| browser_click | Perform a click on an element |
| browser_type | Type into an editable field |
| browser_clear | Clears the value of an input element |
| browser_get_element_text | Gets the text of an element |
| browser_get_attribute | Gets the value of an attribute from an element |
| browser_element_is_displayed | Checks if an element is displayed |
| browser_element_is_enabled | Checks if an element is enabled |
| browser_element_is_selected | Checks if an element is selected |
| browser_switch_to_frame | Switches to an iframe element |
| browser_switch_to_default_content | Switches to the default content |
| browser_switch_to_parent_frame | Switches to the parent iframe |
| browser_file_upload | Uploads a file using a file input element |
| browser_hover | Hover over an element |
| browser_wait_for_element | Wait for an element to be present |
| browser_drag_and_drop | Perform drag and drop between two elements |
| browser_double_click | Perform double click on an element |
| browser_right_click | Perform right click (context click) on an element |
| browser_select_dropdown_by_text | Select dropdown by visible text |
| browser_select_dropdown_by_value | Select dropdown by value |
| browser_key_press | Press a key on the keyboard |
| browser_execute_script | Execute JavaScript in the context of the current page |
| browser_scroll_to_element | Scroll to an element |
| browser_scroll_to_top | Scroll to the top of the page |
| browser_scroll_to_bottom | Scroll to the bottom of the page |
| browser_scroll_to_coordinates | Scroll to specific coordinates |
| browser_scroll_by_pixels | Scroll by a specific number of pixels |
| browser_select_checkbox | Select a checkbox |
| browser_unselect_checkbox | Unselect a checkbox |
| browser_submit_form | Submit a form |
| browser_focus_element | Focus on a specific element |
| browser_blur_element | Remove focus from a specific element |
| browser_screenshot | Take a screenshot of the current page |
| browser_get_cookies | Get all cookies |
| browser_get_cookie_by_name | Get a cookie by name |
| browser_add_cookie_by_name | Add a cookie to the browser |
| browser_set_cookie_object | Set a cookie in the browser |
| browser_delete_cookie | Delete a cookie from the browser |
| browser_delete_cookies | Delete cookies from the browser |