Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
LLM_MODELNoLLM model for synthesis and classification.gpt-4o-mini
POLYG_PORTNoServer port.3000
FALKORDB_HOSTNoFalkorDB host.localhost
FALKORDB_PORTNoFalkorDB port.6379
OPENAI_API_KEYYesRequired. OpenAI API key for LLM and embeddings.
EMBEDDING_MODELNoModel for embeddings.text-embedding-3-small
POLYG_LOG_LEVELNoLog level.info
POLYG_MAX_RETRIESNoNumber of LLM retries with exponential backoff.3
CLASSIFIER_MAX_TOKENSNoMax tokens for intent classifier.1000
FALKORDB_QUERY_TIMEOUTNoMax query execution time in milliseconds.30000
POLYG_PARALLEL_TIMEOUTNoGraph expansion timeout in milliseconds.30000
SYNTHESIZER_MAX_TOKENSNoMax tokens for synthesizer.2000

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/Captain-Jay29/polyg-mcp'

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