Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
MODENoauto, sampling, or direct. auto uses direct HTTP when API_KEY is set and client lacks sampling support.auto
MODELNoModel name hint (e.g. claude-3-5-sonnet, gpt-4o). If empty, no hint sent – MCP host decides.
API_KEYNoLLM API key for direct HTTP mode. Optional for local endpoints, required for remote providers.
TIMEOUTNoSampling timeout in ms (60s for sampling, 120s for direct HTTP).60000 / 120000
BASE_TEMPNoInitial sampling temperature.0.1
CACHE_TTLNoResult cache TTL in ms (default 1 hour). Set to 0 to disable.3600000
LOG_LEVELNoOne of DEBUG, INFO, WARN, ERROR.INFO
COT_PARSERSNoComma-separated parser names to use (e.g., direct-json,fenced-block). Skips others.
MAX_RETRIESNoNumber of retry attempts before returning raw output.2
API_BASE_URLNoBase URL for direct HTTP mode. Default is https://api.openai.com.https://api.openai.com
TEMP_INCREMENTNoTemperature added per retry attempt.0.2
FALLBACK_MODELSNoComma-separated list of fallback models (e.g. gpt-4o,claude-3-5-sonnet). Cycled on failure.
CACHE_MAX_ENTRIESNoMaximum cached results before evicting oldest.100
REASONING_OVERHEADNoFixed token overhead added to the budget formula.800
TRUNCATION_THRESHOLDNoRatio of output/budget that triggers truncation detection.0.95

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/islobodan/cotforce-mcp'

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