Memory Manager MCP server

Manages and switches between memory paths for clients, enabling organized context management across multiple AI projects.
Back to servers
Provider
YU Zongmin
Release date
Jan 12, 2025
Language
Python

This MCP server tool helps you manage and switch between different memory contexts for Claude AI clients. It allows you to maintain separate memory paths for different projects through a simple command-line interface.

Installation

To install the Memory MCP Manager, follow these steps:

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

# Navigate to the project directory
cd memory-mcp-manager

# Make the script executable
chmod +x memory.sh

# Initialize the configuration
./memory.sh init

Basic Configuration

After installation, you'll need to configure your Claude client and memory paths:

Adding a Claude Client

./memory.sh add-client my-claude "/path/to/claude/config.json"

Adding Memory Paths

./memory.sh add project1 "~/projects/project1/memory.jsonl"

Switching Between Memory Paths

./memory.sh switch project1

Available Commands

Client Management

Use these commands to manage your Claude clients:

# Add a new Claude client
./memory.sh add-client <name> <config_path>

# List all configured clients
./memory.sh list-clients

Memory Management

These commands help you manage different memory paths:

# Add a new memory path
./memory.sh add <name> <path>

# Remove an existing memory path
./memory.sh remove <name>

# Switch to a different memory path
./memory.sh switch <name>

# List all available memory paths
./memory.sh list

Configuration File

The tool stores your settings in a config.json file, which contains information about your clients and memory paths:

{
  "clients": [
    {
      "name": "my-claude",
      "config_path": "/path/to/claude/config.json"
    }
  ],
  "memory_paths": {
    "project1": "/path/to/project1/memory.jsonl"
  }
}

How Memory Switching Works

When you switch between memory paths using the switch command, the tool automatically updates all your registered Claude clients to use the selected memory path. This allows you to maintain separate memory contexts for different projects without manually reconfiguring your Claude client each time.

How to add this MCP server to 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 > MCP and click "Add new global MCP server".

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

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

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 explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.

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