Memory MCP Server
A lightweight MCP server that provides persistent key-value storage for AI agents using SQLite and Bun. It enables agents to store, retrieve, and manage memories with optional JSON metadata for long-term context retention.
README
Memory MCP Server
A lightweight MCP (Model Context Protocol) server for persistent agent memory using SQLite and Bun.
Features
- store_memory: Store key-value pairs with optional JSON metadata
- retrieve_memory: Retrieve a memory by its key
- list_memories: List all memories with optional limit
- delete_memory: Delete a memory by its key
Prerequisites
- Bun v1.3.9 or higher
Installation
bun install
Build
bun build src/index.ts --outdir=build --target=bun
Run
bun run src/index.ts
Or use the built version:
bun run build/index.js
Configuration
Environment Variables
MEMORY_DB_PATH: Path to the SQLite database file (default:./memory.db)
MCP Settings Integration
To use this MCP server with Roo Code or Claude Desktop, add the following configuration to your MCP settings file:
Roo Code (Windows): %APPDATA%\roo-code\settings\mcp_settings.json
Claude Desktop (Windows): %APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"memory": {
"command": "bun",
"args": ["/path/to/local-mcp/build/index.js"],
"env": {
"MEMORY_DB_PATH": "/path/to/local-mcp/memory.db"
}
}
}
}
Replace /path/to/local-mcp with the absolute path to this directory.
Usage Examples
Once configured, you can use the memory tools in your MCP client:
Store a memory
store_memory with key="user_preference", value="dark_mode", metadata='{"category":"ui"}'
Retrieve a memory
retrieve_memory with key="user_preference"
List all memories
list_memories
List limited memories
list_memories with limit=10
Delete a memory
delete_memory with key="user_preference"
Project Structure
local-mcp/
├── src/
│ ├── db/
│ │ └── index.ts # Database initialization and types
│ ├── tools/
│ │ ├── store-memory/ # Store memory tool
│ │ ├── retrieve-memory/ # Retrieve memory tool
│ │ ├── list-memories/ # List memories tool
│ │ └── delete-memory/ # Delete memory tool
│ └── index.ts # Main server entry point
├── build/ # Compiled output
├── memory.db # SQLite database (created automatically)
├── .env.example # Environment variables template
├── package.json
├── tsconfig.json
└── README.md
Database Schema
CREATE TABLE memories (
key TEXT PRIMARY KEY,
value TEXT NOT NULL,
metadata TEXT,
created_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP,
updated_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP
);
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.