Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault

No arguments

Capabilities

Features and capabilities supported by this server

CapabilityDetails
tools
{
  "listChanged": true
}
resources
{
  "listChanged": true
}

Tools

Functions exposed to the LLM to take actions

NameDescription
start_browserC

Start a Selenium browser session.

open_urlC

Navigate the active browser session to a URL.

navigateA

Navigate the active browser session to a URL. Alias-friendly alternative to open_url.

clickC

Click an element after waiting for it to be visible and enabled.

interactD

Perform a mouse action on an element.

typeC

Type text into an element after waiting for visibility.

get_textC

Read visible text from an element.

get_attributeC

Read an attribute or property value from an element.

assert_textC

Assert visible element text equals, contains, or matches a regular expression.

assert_visibleC

Assert an element becomes visible.

assert_attributeC

Assert an element attribute/property equals, contains, or matches a regular expression.

wait_for_elementC

Wait for an element to exist, with optional visibility requirement.

wait_until_visibleC

Wait for an element to be visible.

find_elementC

Find an element and return basic metadata. Alias-friendly discovery tool.

retry_clickA

Retry a click for transient UI failures such as stale or intercepted elements.

press_keyC

Press a keyboard key against the active element.

take_screenshotB

Capture a PNG screenshot and optionally save it to disk.

get_current_urlA

Return the current browser URL.

get_titleA

Return the current page title.

get_page_sourceB

Return the current page source, optionally truncated for LLM-friendly output.

capture_pageB

Capture page structure with stable refs (e1, e2, ...) and reusable selectors for follow-up actions.

execute_scriptC

Execute synchronous JavaScript in the current page context.

batch_executeC

Execute a constrained sequence of browser actions in one call. Supported actions: navigate, wait_for_element, click, type, execute_script.

upload_fileC

Send an absolute file path to a file input element.

windowC

Manage browser windows and tabs.

frameB

Switch browser frame focus by index, name/id, selector, parent, or default content.

alertC

Handle browser alert, confirm, or prompt dialogs.

add_cookieC

Add a browser cookie for the current page domain.

get_cookiesA

Get all cookies or one cookie by name.

delete_cookieA

Delete one cookie by name, or all cookies when name is omitted.

session_createC

Create a new browser session and select it as active.

session_selectB

Select an existing browser session as active.

session_listB

List all active browser sessions.

session_destroyC

Destroy a specific browser session.

selector_hint_saveC

Persist a named selector hint for a domain.

selector_hint_getC

Resolve a selector hint by key and domain.

selector_hint_listB

List selector hints, optionally filtered by domain.

selector_hint_deleteC

Delete a selector hint by key and domain.

stop_browserA

Stop the active Selenium browser session if one exists.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription
browser-statusCurrent Selenium browser session status.
accessibility-snapshotCompact DOM-derived accessibility snapshot of visible interactive elements and headings.

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/gaforov/selenium-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server