Skip to main content
Glama
jamesmurdza

Daytona Playwright MCP Server

by jamesmurdza
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
DAYTONA_API_KEYYesYour Daytona API key
DAYTONA_API_URLNoDaytona API server URLhttps://app.daytona.io/api

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

CapabilityDetails
tools
{
  "listChanged": true
}
logging
{}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}
extensions
{
  "io.modelcontextprotocol/ui": {}
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
browser_startA

Start a new browser session in a Daytona sandbox.

This creates a cloud sandbox with Chrome installed, launches the browser, and establishes a connection for remote control. Must be called before using any other browser tools.

browser_stopA

Stop the browser and clean up the Daytona sandbox.

Call this when you're done using the browser to free up resources.

browser_statusB

Check the current status of the browser session.

browser_navigateB

Navigate the browser to a URL.

browser_backB

Navigate back in browser history.

browser_forwardB

Navigate forward in browser history.

browser_refreshB

Refresh the current page.

browser_clickA

Click on an element on the page.

Supports CSS selectors, XPath, and text selectors. Examples:

  • CSS: "button.primary", "#submit-btn", "[data-testid='login']"

  • XPath: "//button[@type='submit']"

  • Text: "text=Sign In", "text=Submit"

browser_typeB

Type text into an input field or editable element.

browser_pressB

Press a keyboard key, optionally on a specific element.

Key examples: Enter, Tab, Escape, Backspace, Delete, ArrowUp, ArrowDown, Control+a, Control+c, Control+v, Shift+Tab, Alt+F4

browser_hoverB

Hover over an element on the page.

browser_selectA

Select an option from a dropdown ( element).

Provide one of: value, label, or index.

browser_scrollB

Scroll the page or a specific element.

browser_screenshotC

Take a screenshot of the current page or a specific element.

Returns the screenshot as an image that can be displayed.

browser_get_textB

Get text content from the page or specific elements.

browser_get_htmlB

Get HTML content from the page or a specific element.

browser_get_attributeB

Get an attribute value from an element.

browser_evaluateA

Execute JavaScript in the page context and return the result.

Examples:

  • "document.title"

  • "window.location.href"

  • "document.querySelectorAll('a').length"

  • "JSON.stringify(localStorage)"

browser_wait_for_selectorB

Wait for an element to reach a specific state.

States:

  • attached: Element is in the DOM

  • detached: Element is removed from the DOM

  • visible: Element is visible on the page

  • hidden: Element is hidden or removed

browser_wait_for_navigationB

Wait for a navigation to complete.

browser_new_tabA

Open a new browser tab and switch to it.

browser_list_tabsA

List all open tabs with their URLs and titles.

browser_switch_tabB

Switch to a different browser tab by index.

browser_close_tabB

Close a browser tab.

browser_upload_fileB

Upload a file to a file input element.

Note: The file must exist on the machine running this MCP server.

browser_download_waitA

Wait for a download to start and complete, returning the downloaded file path.

Call this before triggering the download action.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A3.6/5.0

Scored across 26 tools

Disambiguation5/5

Each tool has a clearly distinct purpose with no ambiguity. For example, browser_click is for clicking, browser_type is for typing, browser_screenshot is for capturing images, and browser_wait_for_selector is for waiting on element states. The descriptions reinforce these distinctions, making misselection unlikely.

Naming Consistency5/5

All tools follow a consistent 'browser_verb' or 'browser_verb_noun' naming pattern (e.g., browser_back, browser_click, browser_screenshot). This uniformity makes the tool set predictable and easy to navigate, with no deviations in style or convention.

Tool Count3/5

With 26 tools, the count feels heavy for a browser automation server, though not extreme. While it covers many operations, some tools could potentially be consolidated (e.g., browser_back and browser_forward are simple navigations), making the set borderline in scope.

Completeness5/5

The tool set provides complete coverage for browser automation, including session management (start, stop, status), navigation, interaction (click, type, hover), inspection (get_html, get_text), and utilities (screenshot, download). There are no obvious gaps, and agents can handle typical workflows without dead ends.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources