Memory MCP

🚀 Memory MCP Server

A Model Context Protocol (MCP) server for storing and retrieving memories using low-level service implementation and SQLite storage.

🚀 Quick Start

✨ Features

• Store and retrieve memories using low - level service implementation and SQLite storage.
• Provide a set of tools for memory management, including storing, retrieving, updating, and deleting memories.
• Offer a convenient command - line tool mcp inspect for debugging and interacting with the MCP server.

📦 Installation

This project uses uv for dependency management instead of pip. uv is a fast and reliable Python package installer and resolver.

Install using uv:

uv pip install memory-mcp

Or install directly from the source code:

uv pip install .

For development:

uv pip install -e ".[dev]"

If you haven't installed uv, please follow the official instructions to install it.

💻 Usage Examples

Basic Usage

Run the Server

memory-mcp

This will start the MCP server, allowing you to store and retrieve memories.

Available Tools

Memory MCP provides the following tools:

• remember: Store a new memory with a title and content.
• get_memory: Retrieve a specific memory by ID or title.
• list_memories: List all stored memories.
• update_memory: Update an existing memory.
• delete_memory: Delete a memory.

Advanced Usage

Debugging with MCP Inspect

MCP provides a convenient command - line tool called mcp inspect for directly debugging and interacting with your MCP server.

Setup

1. First, make sure the MCP CLI tool is installed:

uv pip install mcp[cli]

2. Start the Memory MCP server in one terminal:

memory-mcp

3. In another terminal, use mcp inspect to connect to the running server:

mcp inspect

Using MCP Inspect

After connecting, you can perform the following operations:

List Available Tools

> tools

This will display all the tools provided by the Memory MCP server.

Call Tools

To call a tool, use the call command followed by the tool name and any required parameters:

> call remember title="Meeting Minutes" content="Discussed the project timeline and key milestones."

> call list_memories

> call get_memory memory_id=1

> call update_memory memory_id=1 title="Updated Title" content="Updated content."

> call delete_memory memory_id=1

Development Mode

You can enable debug mode to view detailed request and response information:

> debug on

This helps you understand the exact data transmitted between the server and the client.

Explore Tool Architecture

To view the architecture of a specific tool, do the following:

> tool remember

This will display the input architecture, required parameters, and tool description.

Troubleshooting

If you encounter issues:

1. Check the server logs in the terminal where the server is running for any error messages.
2. Enable debug mode debug on in the MCP inspect terminal to view the raw requests and responses.
3. Ensure that the tool parameters match the expected architecture (check using the tool command).
4. If the server crashes, check for any uncaught exceptions in the terminal where the server is running.

🔧 Technical Details

Development

To contribute to the project, install the development dependencies:

uv pip install -e ".[dev]"

Manage Dependencies

This project uses the uv.lock file to lock dependencies. To update dependencies:

uv pip compile pyproject.toml -o uv.lock

Run Tests

python -m pytest

Code Formatting

black memory_mcp tests

Solvent Check

ruff check memory_mcp tests

Type Checking

mypy memory_mcp