Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
CLAUDE_MODELNoReal backend model used by the gateway.
SANDBOX_ROOTYesRoot directory allowed for worker jobs and analyze file reads.
DIFF_MAX_BYTESNoMaximum returned diff size.
ONEAPI_API_KEYNoPrimary gateway key for OneAPI.
ANTHROPIC_MODELNoReal backend model used by the gateway (alternative).
ONEAPI_BASE_URLNoPrimary gateway URL (OneAPI).
WAIT_DEFAULT_MSNoDefault wait time in milliseconds for job completion.
FALLBACK_API_KEYNoOptional fallback gateway key.
WORKER_ISOLATIONNoSet to 'worktree' for per-job git worktree isolation.
ANTHROPIC_API_KEYNoPrimary gateway key for Anthropic.
CLAUDE_CODE_MODELNoModel name passed to Claude Code for local validation, usually 'sonnet'.
FALLBACK_BASE_URLNoOptional fallback gateway URL.
ANTHROPIC_BASE_URLNoPrimary gateway URL (Anthropic).
USE_OPENAI_ADAPTERNoSet to '1' to use the local Anthropic-to-OpenAI adapter.
WORKER_METRICS_FILENoOptional JSONL path for token usage metrics.
WORKER_ESCALATE_MODELNoOptional stronger model for hard revise passes.
ALLOW_BYPASS_PERMISSIONSNoSet to '1' to allow bypassPermissions (not recommended).

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/sorryorc/mcp-codex-worker'

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