Skip to main content
Glama
nnaveenraju

Sovereign Universal Memory MCP

by nnaveenraju

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
DATABASE_PATHNoFile path for the database if using a local provider~/.universal-memory/memory.db
SEARCH_PROVIDERNoThe search strategy to employ (e.g., 'hybrid')hybrid
VECTOR_PROVIDERNoVector database provider (e.g., 'sqlite-vec', 'pinecone', 'qdrant')sqlite-vec
EMBEDDINGS_MODELNoThe specific model name to use for embeddingsXenova/all-MiniLM-L6-v2
SERVER_TRANSPORTNoTransport protocol for the server (e.g., 'stdio' for Claude Desktop, 'sse' for Docker)stdio
DATABASE_PROVIDERNoDatabase provider implementation (e.g., 'sqlite', 'redis', 'postgres')sqlite
SEARCH_FTS_WEIGHTNoWeight assigned to full-text search in hybrid results0.4
VECTOR_DIMENSIONSNoThe number of dimensions for vector embeddings384
EMBEDDINGS_PROVIDERNoProvider for generating text embeddings (e.g., 'local', 'openai', 'cohere')local
SEARCH_VECTOR_WEIGHTNoWeight assigned to vector similarity in hybrid results0.6

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/nnaveenraju/sovereign-universal-memory-mcp'

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