Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
HEADLESSNoSet to 'true' to run browser headless. Default is false.
OLLAMA_MODELNoOllama model name for local fallback.
PROXY_SERVERNoProxy server URL (e.g., 'http://proxy:8080').
BROWSER_LOCALENoBrowser locale (e.g., 'en-US').
GOOGLE_API_KEYNoGoogle Gemini API key for fallback autonomous tools.
OPENAI_API_KEYNoOpenAI API key for fallback autonomous tools.
OPENAI_BASE_URLNoBase URL for OpenAI-compatible API (e.g., DeepSeek, Groq, Together).
BROWSER_TIMEZONENoBrowser timezone (e.g., 'America/New_York').
BROWSER_VIEWPORTNoViewport dimensions (e.g., '1280x720').
ANTHROPIC_API_KEYNoAnthropic API key for fallback autonomous tools.
BROWSER_USE_MODELNoOverride the default model or provide a sampling model hint.
BROWSER_TRACES_DIRNoPath to save traces.
OPENROUTER_API_KEYNoOpenRouter API key for fallback autonomous tools.
BROWSER_PERMISSIONSNoComma-separated permissions to grant.
BROWSER_TASK_TIMEOUTNoTask timeout in seconds (default 120).
BROWSER_STORAGE_STATENoPath to a file to restore cookies and localStorage from.
BROWSER_USER_DATA_DIRNoPath to browser user data directory.
BROWSER_DOWNLOADS_PATHNoPath to save downloads (default './downloads').
BROWSER_ALLOWED_DOMAINSNoComma-separated list of allowed domains.
BROWSER_RECORD_HAR_PATHNoPath to save HAR file.
BROWSER_RECORD_VIDEO_DIRNoPath to record video.
BROWSER_BLOCK_IP_ADDRESSESNoSet to 'true' to block direct IP navigation.
BROWSER_PROHIBITED_DOMAINSNoComma-separated list of prohibited domains.
BROWSER_WAIT_BETWEEN_ACTIONSNoWait time between actions in seconds.
BROWSER_MINIMUM_WAIT_PAGE_LOAD_TIMENoMinimum wait time for page load in seconds.
BROWSER_WAIT_FOR_NETWORK_IDLE_PAGE_LOAD_TIMENoWait time for network idle in seconds.

Capabilities

Server capabilities have not been inspected yet.

Tools

Functions exposed to the LLM to take actions

NameDescription

No tools

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/Koreahwan/wraith-mcp'

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