mcp-memory-libsql

mcp-memory-libsql

A high-performance, persistent memory system for the Model ContextProtocol (MCP) powered by libSQL. This server provides vector searchcapabilities and efficient knowledge storage using libSQL as thebacking store.

Features

• 🚀 High-performance vector search using libSQL
• 💾 Persistent storage of entities and relations
• 🔍 Semantic search capabilities
• 🔄 Knowledge graph management
• 🌐 Compatible with local and remote libSQL databases
• 🔒 Secure token-based authentication for remote databases

Configuration

This server is designed to be used as part of an MCP configuration.Here are examples for different environments:

Cline Configuration

Add this to your Cline MCP settings:

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

Claude Desktop with WSL Configuration

For a detailed guide on setting up this server with Claude Desktop inWSL, seeGetting MCP Server Working with Claude Desktop in WSL.

Add this to your Claude Desktop configuration for WSL environments:

{
	"mcpServers": {
		"mcp-memory-libsql": {
			"command": "wsl.exe",
			"args": [
				"bash",
				"-c",
				"source ~/.nvm/nvm.sh && LIBSQL_URL=file:/path/to/database.db /home/username/.nvm/versions/node/v20.12.1/bin/npx mcp-memory-libsql"
			]
		}
	}
}

Database Configuration

The server supports both local SQLite and remote libSQL databasesthrough the LIBSQL_URL environment variable:

For local SQLite databases:

{
	"env": {
		"LIBSQL_URL": "file:/path/to/database.db"
	}
}

For remote libSQL databases (e.g., Turso):

{
	"env": {
		"LIBSQL_URL": "libsql://your-database.turso.io",
		"LIBSQL_AUTH_TOKEN": "your-auth-token"
	}
}

Note: When using WSL, ensure the database path uses the Linuxfilesystem format (e.g., /home/username/...) rather than Windowsformat.

By default, if no URL is provided, it will use file:/memory-tool.dbin the current directory.

API

The server implements the standard MCP memory interface withadditional vector search capabilities:

• Entity Management
  • Create/Update entities with embeddings
  • Delete entities
  • Search entities by similarity
• Relation Management
  • Create relations between entities
  • Delete relations
  • Query related entities

Architecture

The server uses a libSQL database with the following schema:

• Entities table: Stores entity information and embeddings
• Relations table: Stores relationships between entities
• Vector search capabilities implemented using libSQL's built-invector operations

Development

Publishing

Due to npm 2FA requirements, publishing needs to be done manually:

1. Create a changeset (documents your changes):

pnpm changeset

2. Version the package (updates version and CHANGELOG):

pnpm changeset version

3. Publish to npm (will prompt for 2FA code):

pnpm release

Contributing

Contributions are welcome! Please read our contributing guidelinesbefore submitting pull requests.

License

MIT License - see the LICENSE file for details.

Acknowledgments

• Built on theModel Context Protocol
• Powered by libSQL