Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
PORTNoHTTP port for streamable-http transport.8051
TRANSPORTNoMCP transport: stdio or streamable-http.streamable-http
RETRIEVAL_MODENoFusion mode (e.g., simple, reciprocal_rerank).reciprocal_rerank
GENERATOR_MODELNoModel name; final model string is <GENERATOR_PROVIDER>/<GENERATOR_MODEL>.gpt-4o-mini
EMBEDDER_BASE_URLNoTEI embedding endpoint.http://127.0.0.1:8080
EMBEDDER_PROVIDERNoEmbedder provider (e.g., tei, openai, ollama).tei
GENERATOR_API_KEYYesLLM provider API key (passed to LiteLLM as api_key). Required.
RERANKER_BASE_URLNoReranker endpoint (TEI cross-encoder).http://pattern-tei-rerank:8080
GENERATOR_PROVIDERNoLiteLLM provider prefix: openai, anthropic, openrouter, etc. See LiteLLM docs.openai
AGENT_PATTERN_JOBS_DBNoSQLite path for async job state (job trio); ephemeral in Docker.~/.config/agent-pattern-mcp/jobs.db
GENERATOR_TEMPERATURENoLLM temperature (all phases).0.1
TASKS_HEARTBEAT_ENABLEDNoEnable heartbeat progress notifications during long tool calls.true
RETRIEVAL_ENABLE_RERANKINGNoEnable TEI cross-encoder reranking.false
TASKS_HEARTBEAT_INTERVAL_SECONDSNoHeartbeat interval in seconds (keep below client idle timeout).30

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

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