Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
DEBUGNoDebug log settings (e.g., mcp:*).
browserUrlNoCommand line argument to connect to a browser via URL (e.g., http://127.0.0.1:9222).
wsEndpointNoCommand line argument to connect to a browser via WebSocket endpoint.
GEMINI_MODELNoThe Gemini model to use (e.g., gemini-2.0-flash-exp).gemini-2.0-flash-exp
OPENAI_MODELNoThe OpenAI model to use (e.g., gpt-4o).gpt-4o
GEMINI_API_KEYNoAPI key for Gemini.
OPENAI_API_KEYNoAPI key for OpenAI.
ANTHROPIC_MODELNoThe Anthropic model to use (e.g., claude-3-5-sonnet-20241022).claude-3-5-sonnet-20241022
BROWSER_CHANNELNoThe browser channel to use (e.g., chrome).
GEMINI_CLI_PATHNoPath to the Gemini CLI.
BROWSER_HEADLESSNoWhether to run the browser in headless mode (true/false).true
BROWSER_ISOLATEDNoWhether to run the browser in isolated mode (true/false).true
ANTHROPIC_API_KEYNoAPI key for Anthropic.
USE_STEALTH_SCRIPTSNoWhether to use stealth scripts to avoid detection (true/false).false
DEFAULT_LLM_PROVIDERNoThe AI provider to use. Valid values: openai, anthropic, or gemini.
REMOTE_DEBUGGING_URLNoThe URL for remote debugging an existing Chrome instance.http://localhost:9222
REMOTE_DEBUGGING_PORTNoThe port for remote debugging.9222
BROWSER_EXECUTABLE_PATHNoThe file path to the Chrome/Chromium executable.

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/NoOne-hub/JSReverser-MCP'

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