Playwright 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
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| browser_navigateC | Navigate to a URL |
| browser_snapshotB | Capture accessibility snapshot of the current page |
| browser_clickC | Click on an element |
| browser_typeC | Type text into an element |
| browser_take_screenshotC | Take a screenshot of the current page |
| browser_closeC | Close the browser |
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 6 tools
Each tool has a clearly distinct purpose targeting specific browser automation actions: clicking, closing, navigating, capturing accessibility snapshots, taking screenshots, and typing text. There is no overlap or ambiguity between these functions.
All tools follow a consistent 'browser_' prefix with descriptive action suffixes (click, close, navigate, snapshot, take_screenshot, type). This uniform snake_case pattern makes the tool set predictable and easy to understand.
Six tools is reasonable for a browser automation server, covering core interactions like navigation, input, and capture. It could be slightly expanded with tools for element selection or waiting, but the current count is well-scoped and manageable.
The tools cover basic navigation, interaction, and capture functions, but there are notable gaps for common automation tasks: no tools for selecting elements (e.g., by CSS/XPath), waiting for conditions, handling alerts/dialogs, or executing JavaScript. This may limit agent effectiveness in complex scenarios.