MCP Memory-libsql

Provides persistent, memory-backed MCP storage with vector search and semantic capabilities using libSQL.

typescript

21

GitHub Stars

typescript

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "joleyline-mcp-memory-libsql": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-memory-libsql"
      ],
      "env": {
        "LIBSQL_URL": "file:/path/to/database.db",
        "LIBSQL_AUTH_TOKEN": "your-auth-token"
      }
    }
  }
}

You run a high-performance MCP server that stores and queries entities, relations, and embeddings using a persistent libSQL-backed store. It provides vector search and semantic capabilities to power context-aware applications and knowledge graphs, while supporting local and remote databases and secure access patterns.

How to use

You interact with this server through an MCP client to manage entities, relations, and vector-based searches. Create, update, or delete entities with embeddings, establish relations between entities, and run semantic searches to find related items. When you connect to a remote libSQL database, you can rely on token-based authentication for secure access. Start the server with the configured command, then point your MCP client to the local or remote data source to begin building your knowledge graph and performing vector-enabled queries.

How to install

Prerequisites you need before installation:

Node.js (recommended latest LTS)
npm or pnpm for package management
Access to a libSQL database (local file-based or remote)

Installation and setup steps you can follow exactly as described here.

Additional sections

Configuration defaults and options let you run the server against a local SQLite database in memory or a persistent file, or against a remote libSQL service. The server exposes an MCP memory interface with enhanced vector search for embeddings and semantic queries, stores entities and relations, and manages a simple knowledge graph.

Available tools

entity_create_update

Create or update entities and their embeddings in the knowledge store.

entity_delete

Delete entities from the store.

entity_search

Search entities by similarity using their embeddings.

relation_create

Create relations between entities to build the knowledge graph.

relation_delete

Delete relations between entities.

relation_query

Query entities related through the knowledge graph.