playwright-mcp-supercharged
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| CAPS | No | Comma-separated capabilities | |
| VISION | No | Enable vision/screenshot capabilities | false |
| BROWSER | No | Browser: chromium, firefox, webkit (default: chromium) | chromium |
| HEADLESS | No | Run in headless mode | false |
| IMAGE_RESPONSES | No | Image responses mode: allow or omit (default: allow) | allow |
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 |
|---|---|
| browser_closeC | Close the page |
| browser_resizeC | Resize the browser window |
| browser_console_messagesC | Returns all console messages |
| browser_handle_dialogD | Handle a dialog |
| browser_evaluateC | Evaluate JavaScript expression on page or element |
| browser_file_uploadC | Upload one or multiple files |
| browser_fill_formC | Fill multiple form fields |
| browser_press_keyC | Press a key on the keyboard |
| browser_typeB | Type text into editable element |
| browser_navigateC | Navigate to a URL |
| browser_navigate_backB | Go back to the previous page in the history |
| browser_network_requestsB | Returns all network requests since loading the page |
| browser_run_codeC | Run Playwright code snippet |
| browser_take_screenshotA | Take a screenshot of the current page. You can't perform actions based on the screenshot, use browser_snapshot for actions. |
| browser_snapshotB | Capture accessibility snapshot of the current page, this is better than screenshot |
| browser_clickC | Perform click on a web page |
| browser_dragC | Perform drag and drop between two elements |
| browser_hoverC | Hover over element on page |
| browser_select_optionC | Select an option in a dropdown |
| browser_tabsB | List, create, close, or select a browser tab. |
| browser_wait_forB | Wait for text to appear or disappear or a specified time to pass |
| session_createA | Create a new browser session. Pass cdpEndpoint to connect to a running Chrome with existing cookies/logins (e.g. "http://localhost:9222"). Without cdpEndpoint, launches a fresh isolated browser. |
| session_listA | List all active browser sessions and show which one is currently active. |
| session_closeA | Close a browser session and dispose its browser context. All tabs and state will be lost. |
| session_switchA | Switch the active session. Subsequent tool calls without an explicit sessionId will use this session. |
| session_import_cookiesA | Import cookies from the user's real Chrome browser into a session. Decrypts cookies from Chrome's encrypted database on macOS. Use this to access sites the user is already logged into. After importing, navigate to the site. If a captcha appears, the user must complete it in the visible browser window. |
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 26 tools
Most tools map to a single distinct action (click, hover, drag, navigate, resize, etc.), so misselection is unlikely. There is mild overlap between browser_type and browser_fill_form, and between browser_evaluate and browser_run_code (JS expression vs Playwright snippet), but descriptions largely clarify intent.
All tool names use consistent snake_case with a clear prefix convention: browser_ for page interactions and session_ for session lifecycle management. Verbs and nouns are predictable throughout.
26 tools is on the heavy side, but each corresponds to a genuinely distinct browser capability (interaction, forms, dialogs, diagnostics, screenshots, sessions, cookies). It is well-scoped for a full Playwright automation surface, only slightly over a comfortable count.
Coverage is strong: navigation, interaction, form filling, dialogs, screenshots/snapshots, console/network diagnostics, tab management, multi-session handling, and cookie import. Minor gaps like explicit cookie export/clear or a scroll tool are easily worked around via browser_run_code or browser_evaluate.