playwright-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 | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| playwright_navigateC | Navigate to a URL,thip op will auto create a session |
| playwright_screenshotC | Take a screenshot of the current page or a specific element |
| playwright_clickC | Click an element on the page using CSS selector |
| playwright_fillC | Fill out an input field |
| playwright_evaluateC | Execute JavaScript in the browser console |
| playwright_click_textB | Click an element on the page by its text content |
| playwright_get_text_contentB | Get the text content of all elements |
| playwright_get_html_contentC | Get the HTML content of the page |
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 8 tools
Most tools target clearly distinct actions (navigate, screenshot, fill, evaluate, extract text/HTML). The only real overlap is playwright_click vs playwright_click_text, but the descriptions (CSS selector vs text content) make the boundary clear enough.
All tools use a consistent playwright_ prefix followed by a snake_case verb or verb_noun pattern (playwright_get_text_content, playwright_get_html_content). No mixed conventions.
Eight tools is well-scoped for basic browser automation: navigation, interaction, and content extraction. Each tool earns its place without redundancy.
Core navigate/interact/extract workflows are covered, but there are notable gaps: no wait/scroll, no back/forward navigation, no select for dropdowns, no hover or key-press, and no session management/close tool despite auto-creating sessions.