Memory

An mcp server that you can use to store and retrieve ideas, prompt templates, personal preferences to use with you favourite AI tool that supports the modelcontextprovider protocol.
  • python

10

GitHub Stars

python

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs
{
  "mcpServers": {
    "drdee-memory-mcp": {
      "command": "memory-mcp",
      "args": []
    }
  }
}

Memory MCP is a server that stores and retrieves memories using a minimal, low-level server backbone with SQLite storage. It lets you save memory entries, fetch them by ID or title, list all memories, and update or delete existing ones, all through a unified MCP interface.

How to use

You run the Memory MCP server locally and connect with an MCP client to store, retrieve, and manage memories. Start the server, then use the built-in tools to interact with memory entries. You can add new memories with a title and content, retrieve a specific memory, list all memories, update an existing entry, or delete memories you no longer need. If you want to experiment or debug, you can inspect available tools and call them directly from an MCP client.

How to install

uv pip install memory-mcp
uv pip install .

For development:

uv pip install -e ".[dev]"

If you don't have uv installed, you can install it following the official instructions.

## Usage notes and common workflows

Start the server in one terminal, then use an MCP client to interact with it. The default workflow involves launching the Memory MCP server and using commands to remember new entries, fetch memories by ID or title, list all memories, update memories, or delete memories as needed.

Debugging and exploration are supported through an MCP inspector tool. You can connect to the running server and list tools, call specific tools with their required parameters, and toggle debug mode to see detailed request and response information.

## Security and maintenance notes

Keep the server up to date with the latest releases to benefit from bug fixes and security patches. When exposing the server over a network, consider authentication and access controls to prevent unauthorized memory modifications.

## Troubleshooting tips

If you encounter issues, check the server console for error messages, enable debug mode in the inspector to see raw requests and responses, verify that tool parameters match the expected input schema, and review any uncaught exceptions reported by the server.

## Available tools

### remember

Store a new memory with a title and content. Provides a new memory entry in the store.

### get\_memory

Retrieve a specific memory by ID or title. Returns the memory content and metadata.

### list\_memories

List all stored memories, showing their IDs and titles for quick reference.

### update\_memory

Update an existing memory by ID or title, allowing changes to the title and content.

### delete\_memory

Delete a memory by ID or title, removing it from storage.
Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational