Memory MCP Server
About
Memory MCP Server is an implementation of the Model Context Protocol (MCP) for managing Claude’s memory and knowledge graph. It uses a SQLite database to persist the knowledge graph and integrates directly with Claude Desktop.
Details
- Author
- MCP-Mirror
- Downloads
- 230
- Categories
- Knowledge Base, AI
Jump to
- Implements Model Context Protocol for memory management.
- Stores knowledge graph in a SQLite database.
- Integrates directly with Claude Desktop.
- Offers both basic and optimized knowledge graph managers.
- Includes a comprehensive test suite with coverage.
- Installed and run easily with uvx.
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
Memory MCP ServerCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Install via uvx memory-mcp-server or by pip from the repository. Set the DATABASE_URL environment variable to your SQLite database URL. For Claude Desktop, add the provided configuration block to claude_desktop_config.json. Run the server with uvx memory-mcp-server.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"memory mcp server": {
"evangstav_python-memory-mcp-server": {
"command": "uvx",
"args": [
"memory-mcp-server"
]
}
}
}
}McpServers
{
"evangstav_python-memory-mcp-server": {
"command": "uvx",
"args": [
"memory-mcp-server"
]
}
}Memory MCP Server
An implementation of the Model Context Protocol (MCP) server for managing Claude's memory and knowledge graph.
Installation
You can install the package using uv:
uvx memory-mcp-server
Or install it from the repository:
uv pip install git+https://github.com/estav/python-memory-mcp-server.git
Usage
Once installed, you can run the server using:
uvx memory-mcp-server
Configuration
The server expects certain environment variables to be set:
- DATABASE_URL: SQLite database URL for storing the knowledge graph
- Add any other configuration variables here...
Integration with Claude Desktop
To use this MCP server with Claude Desktop, add the following to your claude_desktop_config.json:
{
"mcpServers": {
"memory": {
"command": "uvx",
"args": ["memory-mcp-server"]
}
}
}
Development
1. Clone the repository:
git clone https://github.com/estav/python-memory-mcp-server.git
cd python-memory-mcp-server
2. Create a virtual environment and install dependencies:
uv venv
source .venv/bin/activate
uv pip install -e ".[test]" # Include test dependencies
3. Run tests:
pytest # Run all tests
pytest -v # Run with verbose output
pytest -v --cov # Run with coverage report
4. Run the server locally:
python -m memory_mcp_server
Testing
The project uses pytest for testing. The test suite includes:
Unit Tests
-test_knowledge_graph_manager.py: Tests for basic knowledge graph operations
- test_optimized_knowledge_graph_manager.py: Tests for optimized/batch operations
- test_server.py: Tests for MCP server implementation
Running Tests
```bashSign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
