Sovereign Universal Memory MCP
by nnaveenraju
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| DATABASE_PATH | No | File path for the database if using a local provider | ~/.universal-memory/memory.db |
| SEARCH_PROVIDER | No | The search strategy to employ (e.g., 'hybrid') | hybrid |
| VECTOR_PROVIDER | No | Vector database provider (e.g., 'sqlite-vec', 'pinecone', 'qdrant') | sqlite-vec |
| EMBEDDINGS_MODEL | No | The specific model name to use for embeddings | Xenova/all-MiniLM-L6-v2 |
| SERVER_TRANSPORT | No | Transport protocol for the server (e.g., 'stdio' for Claude Desktop, 'sse' for Docker) | stdio |
| DATABASE_PROVIDER | No | Database provider implementation (e.g., 'sqlite', 'redis', 'postgres') | sqlite |
| SEARCH_FTS_WEIGHT | No | Weight assigned to full-text search in hybrid results | 0.4 |
| VECTOR_DIMENSIONS | No | The number of dimensions for vector embeddings | 384 |
| EMBEDDINGS_PROVIDER | No | Provider for generating text embeddings (e.g., 'local', 'openai', 'cohere') | local |
| SEARCH_VECTOR_WEIGHT | No | Weight assigned to vector similarity in hybrid results | 0.6 |
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
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