Selenium MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| navigateA | Navigate to a URL in the browser |
| clickB | Click on an element by CSS selector |
| typeB | Type text into an element by CSS selector |
| get_textB | Get text content of an element by CSS selector |
| wait_for_elementB | Wait for an element to be present by CSS selector |
| screenshotB | Take a screenshot of the current page |
| get_titleA | Get the title of the current page |
| get_urlA | Get the current URL |
| execute_scriptC | Execute JavaScript in the browser |
| close_browserB | Close the browser session |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 10 tools
Each tool targets a distinct action (click, navigate, type, screenshot, etc.) with no overlap. Even CSS-selector-based tools like click, get_text, type, and wait_for_element are clearly separated by their operation.
All tool names follow a consistent snake_case verb_noun pattern (e.g., close_browser, execute_script, wait_for_element). The naming is predictable and easy to understand.
With 10 tools, the set covers essential browser automation actions without being bloated. Each tool earns its place, and the count is appropriate for the domain.
The tools cover core browsing tasks (navigation, interaction, script execution, screenshots, session control). Minor gaps exist, such as retrieving element attributes or handling alerts, but the surface is largely complete for common workflows.