Playwright MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PORT | No | Port the auth gate binds to; Render routes to it. | 10000 |
| MCP_TOKEN | Yes | Required. Bearer token every request must present as `Authorization: Bearer <token>`. The container refuses to start without it. Generated by Render at deploy time (or set manually when running locally, e.g. to `openssl rand -hex 32`). Rotate by editing the value in the Dashboard and updating your clients. | |
| UPSTREAM_PORT | No | Loopback port the MCP server listens on behind the gate. Change only if it collides with something inside the container. | 8931 |
| PLAYWRIGHT_MCP_ALLOWED_HOSTS | No | Comma-separated allowed-hosts value (e.g. `myapp.com,myapp.onrender.com`; `*` disables the check). Only needed if you add a custom domain, since the entrypoint otherwise scopes the host check to your service's own onrender.com hostname via RENDER_EXTERNAL_HOSTNAME. |
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_closeB | Close the page |
| browser_resizeB | Resize the browser window |
| browser_console_messagesB | Returns all console messages |
| browser_handle_dialogC | Handle a dialog |
| browser_evaluateB | Evaluate JavaScript expression on page or element |
| browser_file_uploadB | Upload one or multiple files |
| browser_dropA | Drop files or MIME-typed data onto an element, as if dragged from outside the page. At least one of "paths" or "data" must be provided. |
| browser_fill_formB | Fill multiple form fields |
| browser_press_keyB | Press a key on the keyboard |
| browser_typeB | Type text into editable element |
| browser_navigateC | Navigate to a URL |
| browser_navigate_backA | Go back to the previous page in the history |
| browser_network_requestsA | Returns a numbered list of network requests since loading the page. Use browser_network_request with the number to get full details. |
| browser_network_requestA | Returns full details (headers and body) of a single network request, or a single part if |
| browser_run_code_unsafeA | Run a Playwright code snippet. Unsafe: executes arbitrary JavaScript in the Playwright server process and is RCE-equivalent. |
| 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_clickB | Perform click on a web page |
| browser_dragA | Perform drag and drop between two elements |
| browser_hoverA | Hover over element on page |
| browser_select_optionB | Select an option in a dropdown |
| browser_tabsA | List, create, close, or select a browser tab. |
| browser_wait_forA | Wait for text to appear or disappear or a specified time to pass |
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 23 tools
Most tools target a clearly distinct action (click, hover, type, select_option, navigate, resize), and the network_requests/network_request pair is explicitly differentiated by description. Minor overlap exists between browser_type and browser_fill_form (single vs multiple fields), browser_drag and browser_drop (internal vs external source), and browser_evaluate vs browser_run_code_unsafe (both execute code), but these are adequately disambiguated in practice.
Every tool follows a uniform browser_ snake_case verb/noun pattern (browser_navigate, browser_take_screenshot, browser_select_option). No deviations to camelCase or alternative prefixes, making the naming fully predictable.
23 tools is on the heavier side of the ideal band, but a full browser-automation surface legitimately needs navigation, interaction, form, media, network, tab, and dialog operations. Each tool maps to a real capability, so the count is justified rather than bloated.
Coverage spans navigation/history, interaction (click, hover, drag, drop, type, select, press_key), forms, file upload, screenshots/snapshots, console, network inspection, tabs, dialogs, and waiting. Gaps like cookie/localStorage/session-storage management and viewport sizing via dedicated tools are minor and workable around.