Memory

Provides a dedicated MCP server to manage Claude’s memory and knowledge graph using a SQLite-backed database.

python

1

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": {
    "mcp-mirror-evangstav_python-memory-mcp-server": {
      "command": "uvx",
      "args": [
        "memory-mcp-server"
      ],
      "env": {
        "DATABASE_URL": "sqlite:///memory.db"
      }
    }
  }
}

You run a Memory MCP Server to manage Claude’s memory and knowledge graph. It exposes a dedicated MCP endpoint you can connect to from clients, enabling memory storage, retrieval, and graph-oriented operations tied to Claude’s context.

How to use

You can connect an MCP client to this server to store and query Claude’s memory and knowledge graph. Start the server locally or remotely, then configure your MCP client to point at the server. You’ll typically provide a database URL for persistence and use the standard MCP request patterns supported by your client.

How to install

Prerequisites: you need a runtime environment that supports the MCP server tooling used here.

Install from the package manager you use to run MCP servers.

Option A: install the MCP server using the runtime wrapper ready to run memory-mcp-server.

Option B: install directly from source.

Configuration

The server requires environment configuration to connect to the knowledge graph database.

Set the database URL to point to your SQLite database where the memory graph is stored.

Claude Desktop integration example

To use this MCP server with Claude Desktop, add the following MCP server entry to your Claude Desktop configuration:

{
  "mcpServers": {
    "memory": {
      "command": "uvx",
      "args": ["memory-mcp-server"]
    }
  }
}

Notes and troubleshooting

If you encounter connection issues, verify that the server is running and that the DATABASE_URL environment variable is set to a valid SQLite database URL.

Development and testing (optional)

If you are developing or testing locally, you can start the server in development mode using the standard runtime command and ensure the environment is configured with a temporary database.