Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
PORTNoHTTP server port (default 3500)3500
AUTH_TOKENYesBearer token for client authentication (required)
IDLE_TIMEOUTNoSession idle timeout in ms (default 1800000, 30 min)1800000
WORKSPACE_DIRNoBase directory for sessions; filesystem tools are sandboxed here (default cwd())
RATE_LIMIT_RPMNoMax requests per minute per IP on POST /messages (default 120)120
SSE_IDLE_TIMEOUTNoIdle SSE connection eviction timeout in ms (default 300000, 5 min)300000
MAX_SSE_CONNECTIONSNoMax concurrent SSE connections (default 50)50
CHILD_ENV_OPENAI_API_KEYNoOpenAI API key forwarded to Codex child processes (optional)
CHILD_ENV_ANTHROPIC_API_KEYNoAnthropic API key forwarded to Claude Code child processes (optional)

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/meimakes/pokeclaw'

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