Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
PORTNoPort to run the server on8000
DEBUGNoEnable debug modefalse
TIMEOUTNoWorker timeout in seconds120
WORKERSNoNumber of worker processes4
KEEPALIVENoKeep-alive timeout in seconds5
LOG_LEVELNoLogging level (DEBUG, INFO, WARNING, ERROR, CRITICAL)INFO
USE_CACHENoEnable/disable caching systemtrue
USE_FEEDBACKNoEnable/disable feedback systemtrue
USE_VECTOR_DBNoEnable/disable vector DB integrationtrue
CACHE_MAX_SIZENoMaximum number of items in cache1000
CACHE_TTL_SECONDSNoCache time-to-live in seconds3600
PROMETHEUS_METRICSNoSet to 'true' to expose Prometheus metrics at /metrics
WIKIDATA_VECTORDB_API_KEYNoAPI key for the vector DB service. Required for enhanced semantic search, though the server can function without it through graceful degradation.

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/ebaenamar/wikidata-mcp-mirror'

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