Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
LLM_BASE_URLYesBase URL for OpenAI-compatible LLM endpoint.
ANCHOR_DB_URLYesJDBC URL for Postgres with pgvector.jdbc:postgresql://localhost:5433/anchor
LLM_CHAT_MODELYesChat model name (e.g., gemma-3-4b-it).
ANCHOR_API_TOKENNoBearer token for API authentication; empty = open dev mode.
LM_STUDIO_API_KEYNoOptional bearer token for LM Studio.
LLM_EMBEDDING_MODELYesEmbedding model name (e.g., nomic-embed-text-v1.5, 768-dim).
ANCHOR_WEB_UI_ENABLEDNoEnable web UI.true
ANCHOR_OPENAPI_ENABLEDNoEnable OpenAPI/Swagger UI.true
OTEL_EXPORTER_OTLP_ENDPOINTNoOpenTelemetry OTLP endpoint for traces.http://localhost:4318/v1/traces

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/myrddian/anchor'

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