QCLI Memories MCP

🚀 Q-CLI MCP Memory Server

A contextual memory system for development tools

The MCP Memory Server is a powerful contextual memory system designed specifically for CLI tools, aiming to support developers and cloud engineers. It offers intelligent memory functionality where information persists across different sessions, enabling AI assistants to remember key information about users, preferences, code, and architectural decisions.

🚀 Quick Start

This MCP-based memory system allows AI assistants to gradually build a profound understanding of users and their work. As users interact with the tool, it intelligently stores important details from previous sessions, including:

• Personal preferences and information
• Preferred programming languages and frameworks
• AWS infrastructure patterns and configurations
• Code formatting preferences
• Previous errors and their solutions
• Project-specific requirements

The result is an increasingly personalized experience that adapts to individual workflows, eliminating the need to repeatedly explain technical backgrounds.

Currently, it only supports a local memory database via SQLite. The goal is to also allow cloud-based memory.

📦 Installation

# Clone the repository
git clone https://github.com/yourusername/mcp-memory-server.git

# Navigate to the directory
cd mcp-memory-server

# Install dependencies
pip install -r requirements.txt

# Run the server
python3 mcp_memory_server.py

💻 Usage Examples

Configuring the MCP Server

Add the following configuration to your mcp.json file:

{
    "mcp-server-memories": {
        "command": "python",
        "args": [
            "PATH_TO_YOUR_FILE/memories_server.py"
        ],
        "env": {}
    }
}
Note: Replace PATH_TO_YOUR_FILE with the actual path to your memories_server.py file.

✨ Features

🧠 Intelligent Storage

The system automatically identifies and stores important information from conversations, appropriately categorizing it as:

• #code: Programming languages, frameworks, coding patterns
• #architecture: System design, component relationships, infrastructure decisions
• #personal: User preferences, background information
• #project: Project details, requirements, deadlines

🔍 Contextual Retrieval

Memories can be retrieved in the following ways:

• Exact key lookup
• Keyword search
• Contextual inference

👥 Multi-User Support

The system intelligently:

• Identifies users from the conversation context
• Maintains separate memory spaces for different users
• Allows the potential to share project contexts among users

🔄 Progressive Learning

Memories are built over time, forming an increasingly refined understanding of users:

• Technical preferences
• Project requirements
• Common workflows
• Recurring challenges