MemoryPlugin MCP Server

An MCP (Model Context Protocol) server for MemoryPlugin, enabling AI assistants like Claude to store and retrieve your memories. This server provides a bridge between AI assistants and your MemoryPlugin account, allowing them to:

• Store new memories
• Query existing memories
• Manage memory buckets
• Search across all memories
• Retrieve latest or specific memories
• NEW: Access AI-organized memory categories
• NEW: Get memories from specific categories
• NEW: Smart semantic search capabilities

Setup

Getting Your API Token

1. Go to www.memoryplugin.com/dashboard
2. Find your API token in the dashboard
3. Copy the token for use in configuration

Claude Desktop Configuration

Configure the server in your Claude Desktop configuration file:

Option 1: Using npx (recommended, but currently experiencing issues)

{
  "mcpServers": {
    "memoryplugin": {
      "command": "npx",
      "args": ["-y", "@memoryplugin/mcp-server"],
      "env": {
        "MEMORY_PLUGIN_TOKEN": "your-token-here"
      }
    }
  }
}

Option 2: Using global installation (current workaround)

First, install the package globally:

npm install -g @memoryplugin/mcp-server

Then find your Node.js installation path:

which node
# Example output: /Users/username/.nvm/versions/node/v21.7.3/bin/node

And find the installed package path:

npm root -g
# Look for something like: /Users/username/.nvm/versions/node/v22.14.0/lib/node_modules

Add @memoryplugin/mcp-server/dist/index.js to the end of the path you received in the previous step.

So the final path should look like:

/Users/username/.nvm/versions/node/v22.14.0/lib/node_modules/@memoryplugin/mcp-server/dist/index.js

Use these paths in your configuration:

{
  "mcpServers": {
    "memoryplugin": {
      "command": "/Users/username/.nvm/versions/node/v21.7.3/bin/node",
      "args": [
        "/Users/username/.nvm/versions/node/v21.7.3/lib/node_modules/@memoryplugin/mcp-server/dist/index.js"
      ],
      "env": {
        "MEMORY_PLUGIN_TOKEN": "your-token-here"
      }
    }
  }
}

If you experience any startup issues with Option 2, please use Option 1 with global installation instead.

Available Tools

The MCP server exposes these tools to AI assistants:

1. store_memory

   • Store new memories
   • Optional bucket assignment
   • Automatically prepends current date

2. get_memories

   • Query memories with filters
   • Search functionality
   • Latest/all options
   • Customizable count

3. list_buckets

   • View all memory buckets
   • Includes memory counts

4. create_bucket

   • Create new memory buckets
   • Organize memories by topic/category

5. get_memories_and_buckets

   • Combined query for efficiency
   • Full filtering support
   • Returns both memories and buckets

6. get_memory_categories (NEW)

   • List AI-organized memory categories
   • Shows category summaries and memory counts
   • Helps understand memory organization

7. get_category_memories (NEW)

   • Get memories from specific categories
   • Organized by AI-powered categorization
   • Includes memory details and timestamps

8. smart_search_memories (NEW)

   • Enhanced semantic search
   • AI-powered query understanding
   • Better search results with context

Example Usage

Here are some example prompts you can use with Claude once the server is configured:

Could you store this as a memory: "Had coffee with Sarah at Blue Bottle, discussed upcoming project deadlines"

Can you show me my latest 5 memories?

Could you create a new bucket called "Work Meetings"?

Search my memories for anything related to "coffee meetings"

# NEW Smart Memory Examples:
Show me the categories in my main bucket

What memories do I have in my "Work Projects" category?

Use smart search to find memories about "machine learning"

Support

For any issues or questions, please contact [email protected]