Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
DATABASE_URLNoPostgres connection string. Matches docker-compose.yml's exposed port (5433 on the host, to avoid clashing with a local Postgres on 5432).postgres://memory:memory@localhost:5433/memory
EMBEDDING_DIMNoMust match the embedding model's output dimension and the VECTOR(384) column in schema.sql — change both together.384
EMBEDDING_DTYPENoq8 = ~4x smaller weights, faster CPU inference, small accuracy tradeoff. Use fp32 for full precision.q8
EMBEDDING_MODELNoAny @huggingface/transformers-compatible model.Xenova/bge-small-en-v1.5
MODEL_CACHE_DIRNoPopulated ahead of time by pnpm model:download; otherwise fetched lazily on first use..models/

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/MateoGuerreroE/mcp-memory'

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