Fire in da houseTop Tip:Paying $100+ per month for Perplexity, MidJourney, Runway, ChatGPT and other tools is crazy - get all your AI tools in one site starting at $15 per month with Galaxy AI Fire in da houseCheck it out free

mcp-memory-libsql

MCP.Pizza Chef: joleyline

mcp-memory-libsql is a high-performance persistent memory server for the Model Context Protocol (MCP), powered by libSQL. It offers advanced vector search, semantic knowledge storage, and efficient relationship management, making it ideal for AI agents and knowledge graph applications. It supports both local and remote libSQL databases with secure token-based authentication, enabling scalable and secure knowledge graph management and semantic search workflows.

Use This MCP server To

Store and retrieve semantic knowledge with vector search Manage knowledge graphs with persistent entity and relation storage Enable AI agents to access high-performance memory context Perform semantic search over large datasets efficiently Integrate with local or remote libSQL databases securely Use token-based authentication for secure remote access Support multi-step reasoning with persistent context memory Build AI-enhanced workflows requiring fast knowledge retrieval

README

mcp-memory-libsql

A high-performance, persistent memory system for the Model Context Protocol (MCP) powered by libSQL. This server provides vector search capabilities and efficient knowledge storage using libSQL as the backing store.

Glama badge

Features

  • πŸš€ High-performance vector search using libSQL
  • πŸ’Ύ Persistent storage of entities and relations
  • πŸ” Semantic search capabilities
  • πŸ”„ Knowledge graph management
  • 🌐 Compatible with local and remote libSQL databases
  • πŸ”’ 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 in WSL, see Getting 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 databases through 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 Linux filesystem format (e.g., /home/username/...) rather than Windows format.

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

API

The server implements the standard MCP memory interface with additional 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-in vector operations

Development

Publishing

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

  1. Create a changeset (documents your changes):
pnpm changeset
  1. Version the package (updates version and CHANGELOG):
pnpm changeset version
  1. Publish to npm (will prompt for 2FA code):
pnpm release

Contributing

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

License

MIT License - see the LICENSE file for details.

Acknowledgments

mcp-memory-libsql FAQ

How does mcp-memory-libsql ensure data persistence?
It uses libSQL as a backing store to persistently save entities and relationships for reliable memory across sessions.
Can mcp-memory-libsql perform semantic search?
Yes, it supports semantic vector search to find relevant knowledge based on meaning, not just keywords.
Is remote database access supported?
Yes, it supports connecting to remote libSQL databases with secure token-based authentication.
What kind of authentication does it use for remote access?
It uses secure token-based authentication to ensure safe and authorized connections.
Can it handle knowledge graph management?
Yes, it efficiently manages entities and their relationships, enabling knowledge graph construction and querying.
Is mcp-memory-libsql compatible with local databases?
Yes, it works with both local and remote libSQL databases seamlessly.
How does it improve AI agent workflows?
By providing fast, persistent, and semantic memory access, it enables AI agents to perform multi-step reasoning and context-aware tasks.
What LLM providers can it integrate with?
It is provider-agnostic and can integrate with LLMs like OpenAI, Claude, and Gemini.