Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
DEFAULT_MODELNoDefault model to use for tasks. Defaults to 'auto' which picks per task.auto
CODEX_CLI_PATHNoOptional path to the Codex CLI executable. Defaults to searching PATH.
DISABLED_TOOLSNoComma-separated list of disabled tools. Default: 'analyze,refactor,testgen,secaudit,docgen,tracer'.analyze,refactor,testgen,secaudit,docgen,tracer
GEMINI_CLI_PATHNoOptional path to the Gemini CLI executable. Defaults to searching PATH.
OPENROUTER_API_KEYNoOpenRouter API key for fallback. Required if neither Gemini CLI nor Codex CLI is installed.
CLI_TIMEOUT_SECONDSNoTimeout in seconds for CLI commands. Defaults to 120.120
OPENROUTER_ALLOWED_MODELSNoComma-separated list of allowed models via OpenRouter. Empty means no restrictions.
DEFAULT_THINKING_MODE_THINKDEEPNoDefault thinking mode level for thinkdeep tool. Defaults to 'high'.high

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/dgdev25/mesh'

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