Skip to main content
Book a demo

Playwright

Test web apps in a real browser that your AI client drives with Playwright.

Book a demo View documentation

Tools

27 available tools

Search the tool definitions captured from the MCP server. The live list can vary with version, deployment, and credentials.

27 tools found.

  • Browser click

    Tool name: browser_click

    Perform click on a web page

  • Browser close

    Tool name: browser_close

    Close the page

  • Browser console messages

    Tool name: browser_console_messages

    Returns all console messages

  • Browser drag

    Tool name: browser_drag

    Perform drag and drop between two elements

  • Browser drop

    Tool name: browser_drop

    Drop files or MIME-typed data onto an element, as if dragged from outside the page.

  • Browser emulate media

    Tool name: browser_emulate_media

    Emulate CSS media features for the page, for example switch between the light and dark color scheme.

  • Browser evaluate

    Tool name: browser_evaluate

    Evaluate JavaScript expression on page or element

  • Browser file upload

    Tool name: browser_file_upload

    Upload one or multiple files

  • Browser fill form

    Tool name: browser_fill_form

    Fill multiple form fields

  • Browser find

    Tool name: browser_find

    Search the accessibility snapshot of the current page for text or a regular expression.

  • Browser handle dialog

    Tool name: browser_handle_dialog

    Handle a dialog

  • Browser hover

    Tool name: browser_hover

    Hover over element on page

  • Browser navigate

    Tool name: browser_navigate

    Navigate to a URL

  • Browser navigate back

    Tool name: browser_navigate_back

    Go back to the previous page in the history

  • Browser network request

    Tool name: browser_network_request

    Returns full details (headers and body) of a single network request, or a single part if part is set.

  • Browser network requests

    Tool name: browser_network_requests

    Returns a numbered list of network requests since loading the page.

  • Browser press key

    Tool name: browser_press_key

    Press a key on the keyboard

  • Browser resize

    Tool name: browser_resize

    Resize the browser window

  • Browser run code unsafe

    Tool name: browser_run_code_unsafe

    Run a Playwright code snippet.

  • Browser select option

    Tool name: browser_select_option

    Select an option in a dropdown

  • Browser snapshot

    Tool name: browser_snapshot

    Capture accessibility snapshot of the current page, this is better than screenshot

  • Browser tabs

    Tool name: browser_tabs

    List, create, close, or select a browser tab.

  • Browser take screenshot

    Tool name: browser_take_screenshot

    Take a screenshot of the current page.

  • Browser type

    Tool name: browser_type

    Type text into editable element

  • Browser wait for

    Tool name: browser_wait_for

    Wait for text to appear or disappear or a specified time to pass

  • Browser webmcp call

    Tool name: browser_webmcp_call

    Call a WebMCP tool registered by the page.

  • List browser webmcp

    Tool name: browser_webmcp_list

    List the WebMCP tools registered by the page, across all frames

Compatibility

Connect Playwright to the clients your teams already use

19 AI clients can connect to Playwright through Runlayer. Pick one for its setup steps and controls.

CursorVS CodeClaude CodeWindsurfGooseCodexHermesRaycastWarpGitHub CopilotGitHub Copilot CLIGemini CLIZedCline CLIAntigravityOpenCodeCrushECAOh My Pi

Why Runlayer

Why connect Playwright through Runlayer?

One approved path

Approve Playwright once and everyone gets it in the AI clients they already use. Runlayer holds the credentials, so nothing sits in client configuration.

Fine-grained policy

Control who can use each server, tool, and resource, and under which runtime conditions.

Runtime security

Scan tool inputs and outputs for prompt injection, credential exposure, PII, and data exfiltration, then alert, mask, or block.

Audit and observability

Trace every request across users, clients, tools, policies, scanner decisions, and downstream systems.

Frequently asked questions