Personal Memory MCP Server
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Personal Memory MCP ServerRemember that my favorite coffee is cappuccino"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Personal Memory MCP Server
A modern MCP (Model Context Protocol) server that provides Claude Desktop with the ability to store and retrieve personal information locally.
Features
Personal Information: Store and retrieve basic personal details
Preferences: Organize preferences by category (food, music, work, etc.)
Memories: Store memories with tags and context for easy searching
Relationships: Track information about people you know
Goals: Manage personal and professional goals with status tracking
Local Storage: All data stored securely in a local JSON file
Related MCP server: Claude Memory MCP
Quick Start
Prerequisites
Python 3.10 or higher
uv package manager
Installation
Clone or download this project
Install uv if you haven't already:
curl -LsSf https://astral.sh/uv/install.sh | shSet up the project:
cd personal-memory-mcp
uv syncConfiguration
Add this to your Claude Desktop configuration file:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%/Claude/claude_desktop_config.json
Linux: ~/.config/Claude/claude_desktop_config.json
{
"mcpServers": {
"personal-memory": {
"command": "uv",
"args": ["run", "memory-server"],
"cwd": "/path/to/personal-memory-mcp"
}
}
}Replace /path/to/personal-memory-mcp with the actual path to your project directory.
Usage
After configuration, restart Claude Desktop. You can then use natural language to interact with your memory:
"Remember that my favorite coffee is cappuccino"
"Store that I met Sarah at the conference - she's a data scientist"
"Add a goal to learn Spanish by the end of the year"
"What do you remember about my food preferences?"
"Show me my active goals"
Testing the Server
You can test the server functionality with the MCP Inspector:
uv run mcp dev server.pyDevelopment
Running Tests
uv run pytestCode Formatting
uv run black .
uv run ruff check .Running the Server Directly
uv run python memory_server.pyData Storage
All personal data is stored locally in personal_memory.json in the project directory. The file includes:
Personal information (name, location, etc.)
Categorized preferences
Timestamped memories with tags
Relationship information
Goals with status tracking
Privacy & Security
Local Only: All data stays on your machine
No Network: No data transmitted to external servers
Full Control: You own and control all your data
Backup Friendly: Simple JSON format for easy backup
License
MIT License - see LICENSE file for details.
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/Joopsnijder/personal-memory-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server