https://github.com/mekanixms/mcp_memory_plugin
https://github.com/mekanixms/mcp_memory_plugin
Last synced: 3 months ago
JSON representation
- Host: GitHub
- URL: https://github.com/mekanixms/mcp_memory_plugin
- Owner: mekanixms
- License: mit
- Created: 2025-02-15T07:01:13.000Z (8 months ago)
- Default Branch: main
- Last Pushed: 2025-02-15T07:24:25.000Z (8 months ago)
- Last Synced: 2025-02-15T08:23:57.956Z (8 months ago)
- Language: Python
- Size: 7.81 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE.txt
Awesome Lists containing this project
README
# Memory Plugin
A Python-based memory plugin that uses SQLite for persistent storage.
## Overview
This plugin provides memory storage functionality using SQLite as the backend database. It's designed to store and manage data persistently across sessions.
## Setup
1. **Environment Configuration**
Create a `.env` file in the root directory with the following configuration:
```
MEMORY_DB_PATH=/path/to/your/memory.sqlite
```
You can use the provided `.env.example` as a template:
```bash
cp .env.example .env
```
2. **Dependencies**
The project requires Python and uses SQLite for data storage. Make sure you have Python installed on your system.
## Configuration
1. rename .env.example to .env and edit the values to your needs:
2. Locate claude_desktop_config.json and use the template below to add "MQTT Bridge" to the mcpServers section.
MacOs: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: C:\Users\\AppData\Roaming\Claude\claude_desktop_config.json
```json
{
"mcpServers": {
"memory_recall": {
"command": "/path/to/python3",
"args": [
"/path/2/your/cloned/repository/memory_plugin.py"
]
}
}
}
```
The SQLite database path is configured through the `MEMORY_DB_PATH` environment variable. This should point to where you want the SQLite database file to be stored.
Current configuration:
```
MEMORY_DB_PATH=/path/to/your/dabatase.sqlite
```
## Usage
### Basic Usage
Refer to the @mcp.resource and @mcp.tool decorated functions in the memory_plugin.py file
Examples to type in the chat:
* `memory://load` to load the saved memories at new chat start
* `Save into the memory, under aNewName category, the following: a new message with important info to remember`
* `Save the relevant points of the conversation into the memory under aNewName category`
## Development
When contributing to this project:
1. Make sure to not commit sensitive information
2. Keep your `.env` file private
3. Use `.env.example` for sharing template configurations
## License
This project is licensed under the MIT License.