Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
LOG_LEVELNoControl log verbosity (debug|info|warn|error)info
ENABLE_GPUNoEnable WebGPU acceleration tier (not yet implemented)false
ENABLE_WASMNoEnable WASM acceleration tiertrue
MAX_WORKERSNoMaximum concurrent workersCPU cores - 1
MIN_WORKERSNoMinimum workers to keep alive (set to 0 for auto-scaling)2
TASK_TIMEOUTNoTask timeout in milliseconds30000
ENABLE_WORKERSNoEnable WebWorkers acceleration tiertrue
MAX_MATRIX_SIZENoMaximum matrix dimension (1000×1000)1000
MAX_ARRAY_LENGTHNoMaximum array length for statistics100000
MAX_NESTING_DEPTHNoMaximum parentheses/bracket nesting50
OPERATION_TIMEOUTNoOperation timeout in milliseconds30000
NOTIFY_DEGRADATIONNoLog when acceleration tier degradation occurstrue
ENABLE_PERF_LOGGINGNoEnable periodic performance statistics logging
WORKER_IDLE_TIMEOUTNoIdle timeout in ms before worker termination60000
DISABLE_PERF_TRACKINGNoDisable performance tracking for minimal overhead
MAX_EXPRESSION_LENGTHNoMaximum expression length (characters)10000
DISABLE_WASM_INTEGRITYNoDisable WASM integrity checks (development only)

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/danielsimonjr/math-mcp'

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