Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
DATABASE_URLYesPostgreSQL connection string (e.g., postgresql://user:pass@host:5432/db). Falls back to local SQLite if not set.
DEFAULT_MODELNoChat model to use (default: gpt-4o-mini).gpt-4o-mini
OPENAI_API_KEYYesAPI key for OpenAI embeddings and chat completions. Required for live runs.
LANGSMITH_API_KEYNoAPI key for LangSmith tracing (optional).
LANGSMITH_TRACINGNoEnable LangSmith tracing (optional, set to 'true' to enable).
CHROMA_PERSIST_DIRNoDirectory for Chroma vector store persistence (default: ./data/chroma)../data/chroma
EVAL_MIN_GROUNDEDNESSNoMinimum groundedness score to pass (default: 0.80).0.80
DEFAULT_EMBEDDING_MODELNoEmbedding model to use (default: text-embedding-3-small).text-embedding-3-small
EVAL_MAX_LATENCY_SECONDSNoMaximum latency in seconds to pass (default: 5).5
EVAL_MIN_RETRIEVAL_SCORENoMinimum retrieval quality score to pass (default: 0.75).0.75
EVAL_MAX_HALLUCINATION_RISKNoMaximum hallucination risk score to pass (default: 0.20).0.20

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/AbhinavVarma02/Agentops-Evalbench-MCP'

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