Schema | Playwright Vision MCP Server

Playwright Vision MCP Server

Describes the environment variables required to run the server.

Name	Required	Description	Default
`PORT`	No	HTTP server port	4201
`BROWSER_TYPE`	No	Browser engine to use (chromium, firefox, webkit)	chromium
`MCP_AUTH_TOKEN`	No	Authentication token for HTTP server (optional)
`OPENAI_API_KEY`	No	OpenAI API key (required for analyze_image tool)
`SCREENSHOT_DIR`	No	Directory for saving screenshots	./screenshots
`OPENAI_BASE_URL`	No	Optional custom base URL for OpenAI-compatible APIs	https://api.openai.com/v1
`OPENAI_VISION_MODEL`	No	Vision model for analyze_image tool	gpt-4.1-mini
`PLAYWRIGHT_HEADLESS`	No	Run browser in headless mode (true/false)	true

Features and capabilities supported by this server

Capability	Details
`tools`	{ "listChanged": true }
`logging`	{}

Functions exposed to the LLM to take actions

Name	Description
navigate_urlC	Navigate to a URL using a server-managed session and analyze sections and internal links
click_elementB	Click on elements using the server-managed session
get_contentB	Extract content from the page using the server-managed session
close_sessionA	Close all browser sessions managed by the server and clear current session
run_playwrightA	Execute custom async Playwright code using the server-managed session

Interactive templates invoked by user choice

Name	Description
No prompts

Contextual data attached and managed by the client

Name	Description
No resources

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/davidkim9/playwright-vision-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server