Memory Plus MCP server for AI agents

Memory-Plus is a lightweight, local Retrieval-Augmented Generation (RAG) memory store for MCP agents that allows your AI assistant to maintain persistent memories across conversations. It enables your agent to record, retrieve, update, and visualize "memories" including notes, ideas, and important context from previous interactions.

Prerequisites

Google API Key Setup

You'll need a Google API key to use the Gemini Embedding API (which is free to use):

Obtain a key from Google AI Studio
Set it as an environment variable:

# macOS/Linux
export GOOGLE_API_KEY="<YOUR_API_KEY>"

# Windows (PowerShell)
setx GOOGLE_API_KEY "<YOUR_API_KEY>"

UV Runtime

The UV runtime is required to serve the MCP plugin:

pip install uv

Or install via shell scripts:

# macOS/Linux
curl -LsSf https://astral.sh/uv/install.sh | sh

# Windows (PowerShell)
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"

Installation in VS Code

The simplest way to install Memory-Plus is through VS Code's one-click setup:

Click the One Click Install in VS Code badge

This will add the following to your settings.json:

{
  "mcpServers": {
    "memory-plus": {
      "command": "uvx",
      "args": [
        "-q",
        "memory-plus@latest"
      ],
    }
  }
}

If you need to add your Google API key manually, include it as an environment variable:

"env": {
  "GOOGLE_API_KEY": "<YOUR_API_KEY>"
}

Installation in Other Environments

Cursor

Go to file -> Preferences -> Cursor Settings -> MCP and add the configuration:

"memory-plus": {
  "command": "uvx",
  "args": [
    "-q",
    "memory-plus@latest"
  ],
  "env": {
    "GOOGLE_API_KEY": "<YOUR_API_KEY>"
  }
}

Cline

Add to your cline_mcp_settings.json:

{
  "mcpServers": {
    "memory-plus": {
      "disabled": false,
      "timeout": 300,
      "command": "uvx",
      "args": [
        "-q",
        "memory-plus@latest"
      ],
      "env": {
        "GOOGLE_API_KEY": "${{ secrets.GOOGLE_API_KEY }}"
      },
      "transportType": "stdio"
    }
  }
}

Local Testing

You can test Memory-Plus locally using the MCP Inspector:

git clone https://github.com/Yuchen20/Memory-Plus.git
cd Memory-Plus
npx @modelcontextprotocol/inspector fastmcp run run .\memory_plus\mcp.py

Using with a Chatbot

Memory-Plus includes a template chatbot in agent.py:

# Clone the repository
git clone https://github.com/Yuchen20/Memory-Plus.git
cd Memory-Plus

# Install dependencies
pip install uv
uv pip install fast-agent-mcp
uv run fast-agent setup

Configure fastagent.config.yaml and fastagent.secrets.yaml with your API keys, then run:

uv run agent_memory.py

Key Features and Usage

Memory-Plus provides several powerful capabilities:

Recording Memories

Your agent can save important information, ideas, and context from conversations for future reference.

Retrieving Memories

Search for relevant memories by keywords or topics from past conversations.

Recent Memories

Quickly access the last N interactions to maintain conversation continuity.

Updating Memories

Append to or modify existing memory entries as conversations evolve.

Visualizing Memories

View an interactive graph visualization that reveals relationships between different memories.

Document Import

Import external documents directly into the agent's memory store.

Memory Management

Delete unwanted entries and access version history for updated memories.

Troubleshooting

If Memory-Plus isn't working:

The first run may take about a minute to download all required dependencies
Subsequent runs will be much faster
For other issues, open an issue on the GitHub repository

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "memory-plus" '{"command":"uvx","args":["-q","memory-plus@latest"]}'

See the official Claude Code MCP documentation for more details.

For 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 > Tools & Integrations and click "New MCP Server".

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

{
    "mcpServers": {
        "memory-plus": {
            "command": "uvx",
            "args": [
                "-q",
                "memory-plus@latest"
            ]
        }
    }
}

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

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your 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

2. Add this to your configuration file:

{
    "mcpServers": {
        "memory-plus": {
            "command": "uvx",
            "args": [
                "-q",
                "memory-plus@latest"
            ]
        }
    }
}

3. Restart Claude Desktop for the changes to take effect