🧠 AI Memory/Docs/PyPI Setup
v1.5.0MIT LicensePyPI

PyPI Setup: AI Memory MCP Server

Install the MCP server in 10 seconds with one pip install command. No configuration files. No accounts. No API keys.

⚡ Quick Install

$ pip install aimemory-mcp-server
$ aimemory-mcp-server

✓ Python 3.8+ ✓ macOS / Linux / Windows ✓ No API keys needed ✓ MIT License

📦 View on PyPI →

Table of Contents

Prerequisites

  • Python 3.8+ — Check with python --version or python3 --version
  • pip — Check with pip --version or pip3 --version
  • Operating System — macOS, Linux, or Windows (WSL recommended for Windows)

Installation

Install the package from PyPI:

pip install aimemory-mcp-server

This installs the aimemory-mcp-server package and all dependencies (SQLite bindings, MCP SDK, etc.).

💡 Platform-specific notes:

  • macOS: Use pip3 instead of pip if Python 2 is default
  • Linux: You may need pip3 install aimemory-mcp-server
  • Windows: Use py -m pip install aimemory-mcp-server or install via WSL

Running the Server

Start the MCP server:

aimemory-mcp-server

The server starts and listens on stdio (standard MCP transport). It creates a SQLite database at ~/.aimemory/memories.db on first run.

Claude Desktop Configuration

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "ai-memory": {
      "command": "aimemory-mcp-server"
    }
  }
}

Restart Claude Desktop. Try asking: "Search my memories for React performance tips"

Cursor Configuration

  1. Open Cursor
  2. Go to Settings → MCP → Add New MCP Server
  3. Set Name: AI Memory
  4. Set Type: stdio
  5. Set Command: aimemory-mcp-server
  6. Click Add

Cursor will now have access to all 12 memory tools.

Windsurf Configuration

Add to your MCP configuration:

{
  "mcpServers": {
    "ai-memory": {
      "command": "aimemory-mcp-server"
    }
  }
}

VS Code (Cline / Continue) Configuration

In your MCP settings file (typically ~/.vscode/mcp.json or via the extension settings UI):

{
  "mcpServers": {
    "ai-memory": {
      "command": "aimemory-mcp-server"
    }
  }
}

Troubleshooting

Command not found: aimemory-mcp-server

The binary may not be in your PATH. Try:

python -m aimemory_mcp.server

Or reinstall with pip install --user aimemory-mcp-server to ensure it's in your user bin directory.

MCP client can't connect

  • Ensure the server is running (you should see log output in the terminal)
  • Check the command path in your client configuration
  • Restart your AI client after changing MCP configuration
  • Check that aimemory-mcp-server works standalone in a terminal

Database permission errors

The server creates its database at ~/.aimemory/. Ensure this directory is writable:

mkdir -p ~/.aimemory chmod 755 ~/.aimemory

Updating

To update to the latest version:

pip install --upgrade aimemory-mcp-server

Check the changelog for version history.

🚀 Ready to go?

Your AI now has persistent memory! Try it out by asking your AI to search for past conversations, save important insights, or retrieve your tech stack preferences.