Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
PROXY_PASSNoPassword for proxy authentication
PROXY_USERNoUsername for proxy authentication
PROXY_SERVERNoThe proxy server URL (e.g., http://1.2.3.4:8080 or socks5://1.2.3.4:1080)

Capabilities

Features and capabilities supported by this server

CapabilityDetails
tools
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
list_pages

List all open browser pages/tabs

new_page

Create a new browser page/tab, optionally navigating to a URL

select_page

Set a page as the active page for subsequent operations

close_page

Close a browser page/tab

navigate_page

Navigate to a URL or go back/forward/reload

take_snapshot

Take a text snapshot of the page with interactive element UIDs for targeting

take_screenshot

Take a screenshot of the page or a specific element

evaluate_mainworld

Execute JavaScript in the page's MAIN execution context (same as browser DevTools console).

USE THIS TOOL WHEN YOU NEED TO:

  • Access window globals like window.NUXT, window.NEXT_DATA, window.APP_STATE

  • Read framework hydration state (Next.js, Nuxt.js, Vue, React, etc.)

  • Access variables/functions defined by the page's own scripts

  • Interact with third-party libraries loaded by the page (jQuery, etc.)

CRITICAL LIMITATIONS:

  • NO async/await support - scripts must be SYNCHRONOUS only

  • NO Promise, fetch(), setTimeout callbacks

  • Script will be REJECTED if it contains async patterns

EXAMPLES:

  • "window.NUXT" → Returns Nuxt.js state

  • "window.NEXT_DATA" → Returns Next.js props

  • "typeof jQuery !== 'undefined' ? jQuery.fn.jquery : null" → Check jQuery version

evaluate_isolated

Execute JavaScript in an ISOLATED context (sandboxed, separate from page scripts).

USE THIS TOOL WHEN YOU NEED TO:

  • Make async operations (fetch, setTimeout, Promises)

  • Query/manipulate the DOM without affecting page state

  • Run code that shouldn't interfere with page scripts

  • Perform async data extraction or waiting

LIMITATIONS:

  • CANNOT access window globals (window.NUXT, etc. will be undefined)

  • CANNOT call functions defined by page scripts

  • Only has access to DOM and standard browser APIs

EXAMPLES:

  • "await fetch('/api/data').then(r => r.json())" → Make API calls

  • "document.querySelectorAll('.item').length" → Count elements

  • "await new Promise(r => setTimeout(r, 1000))" → Wait/delay

get_framework_state

Extract Next.js/Nuxt.js hydration state from the page

click

Click an element by its UID from snapshot

hover

Hover over an element by its UID

fill

Fill a form field (input, textarea, select) by its UID

fill_form

Fill multiple form fields at once

press_key

Press a keyboard key or combination

drag

Drag an element to another element

wait_for

Wait for text or selector to appear on the page

wait_for_navigation

Wait for page navigation to complete

dismiss_popups

Dismiss cookie consent popups and overlays

get_page_text

Extract text content from the page

reload_settings

Reload settings from config file

get_config_paths

Get all config file paths (user config, package default, active)

init_user_config

Initialize user config directory (~/.config/camoufox-mcp) with default settings

start_recording

Start recording user interactions (clicks, scrolls, inputs)

stop_recording

Stop recording and return captured actions

get_recording_status

Get current recording status

start_network_capture

Start capturing network requests

stop_network_capture

Stop capturing network requests

get_network_logs

Get captured network request logs

clear_network_logs

Clear captured network logs

intercept_network

Intercept and block/modify network requests

remove_intercept

Remove network intercept rules

start_console_capture

Start capturing browser console messages

stop_console_capture

Stop capturing console messages

get_console_logs

Get captured console messages

clear_console_logs

Clear captured console logs

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Latest Blog Posts

MCP directory API

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

curl -X GET 'https://glama.ai/api/mcp/v1/servers/baixianger/camoufox-mcp'

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