Long-Term Memory MCP server

Provides long-term memory storage using SQLite and vector embeddings, enabling persistent context across conversations, development decision preservation, and knowledge base building through semantic search capabilities.
Back to servers
Setup instructions
Provider
Tom Schell
Release date
Mar 20, 2025
Language
TypeScript
Stats
6 stars

This MCP server provides long-term memory for LLMs, allowing them to retain context across multiple sessions through semantic search with embeddings. It organizes project history, code changes, and important decisions in a searchable format that follows the Model Context Protocol (MCP) standard.

Prerequisites

  • Node.js (v18 or later)
  • Ollama running locally (for embeddings)
    • Must have the nomic-embed-text model installed
  • SQLite3

Installation

  1. Clone the repository
  2. Install dependencies:
    npm install
    
  3. Build the project:
    npm run build
    
  4. Create a .env file with required configuration:
    OLLAMA_HOST=http://localhost:11434
    DB_PATH=memory.db
    

Usage

Starting the Server

Start the server in development mode:

npm run dev

This will compile TypeScript, copy schema files, and start the server with auto-reload. The server connects via stdio for Cursor compatibility.

Available MCP Tools

The server provides several tools through the MCP protocol:

Store Development Memory

Create new development memories with:

  • Content
  • Type (conversation/code/decision/reference)
  • Tags
  • Code changes
  • Files created/modified
  • Key decisions
  • Implementation status

List Development Memories

List existing memories with optional tag filtering.

Get Development Memory

Retrieve specific memory by ID.

Search Memories

Perform semantic search across memories using embeddings.

Memory Organization

The system organizes information in several ways:

  • Project-based memory: All context is organized by project
  • Memory types:
    • Conversations: Dialog context and important discussions
    • Code: Implementation details and changes
    • Decisions: Key architectural and design choices
    • References: Links to external resources and documentation
  • Rich metadata including:
    • Implementation status
    • Key decisions
    • Files created/modified
    • Code changes
    • Dependencies added
  • Tagging system for memory organization
  • Relationship tracking between memories

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "mcp-long-term-memory" '{"command":"npx","args":["-y","mcp-long-term-memory"]}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "mcp-long-term-memory": {
            "command": "npx",
            "args": [
                "-y",
                "mcp-long-term-memory"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%\Claude\claude_desktop_config.json
  • Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "mcpServers": {
        "mcp-long-term-memory": {
            "command": "npx",
            "args": [
                "-y",
                "mcp-long-term-memory"
            ]
        }
    }
}

3. Restart Claude Desktop for the changes to take effect

Want to 10x your AI skills?

Get a free account and learn to code + market your apps using AI (with or without vibes!).

Nah, maybe later