Schema | apex-browser-mcp

apex-browser-mcp

Describes the environment variables required to run the server.

Name	Required	Description	Default
`APEX_BROWSER_PORT`	No	Port for HTTP transport	3010
`APEX_BROWSER_SHOTS`	No	Directory for screenshots	/tmp
`APEX_BROWSER_HEADLESS`	No	Run headless: 1=headless, 0=headed	0
`APEX_BROWSER_TRANSPORT`	No	Transport mode: stdio or http	stdio
`APEX_BROWSER_MAX_SESSIONS`	No	Maximum number of concurrent browser sessions	15

Features and capabilities supported by this server

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

Functions exposed to the LLM to take actions

Name	Description
browser_new_sessionA	Open an isolated browser session. engine: chrome (real Chrome) \| chromium \| webkit (Safari engine, multi) \| safari (real Safari.app, single-session). Returns a session id.
browser_attachA	Attach to a Chrome already running with --remote-debugging-port. mode: default (adopt your logged-in session — real cookies) \| isolated (fresh stealthed context on the same Chrome). Returns a session id usable with all other tools.
browser_navigateC	Go to a URL in a session.
browser_snapshotC	Title, URL, and indexed interactive elements (ref=e1,e2,...). Use a ref with click/type.
browser_clickC	Click an element by ref from the latest snapshot.
browser_typeC	Fill text into an element by ref; submit:true presses Enter.
browser_evaluateC	Run a JS expression in the page, return the result.
browser_screenshotC	Save a PNG of the current view, return its path.
browser_list_sessionsA	List all open sessions with engine and current URL.
browser_close_sessionC	Close and free a 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/apexradius/browser-mcp'

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