Skip to main content
asad
Written by asad
Last updated 1 month ago
MemoryPlugin can be used across dozens of AI tools through our MCP Server implementation.
Claude Desktop is one of the most popular MCP clients since Anthropic created the MCP protocol, but there are 100+ other tools that support MCP.

​
What is MCP?

Model Context Protocol is a system developed by Anthropic to standardize how AI systems communicate with external data sources and tools. MCP works with two components:
  • MCP Clients: The applications you use to interact with AI (like Claude Desktop, Cursor, Windsurf, etc.)
  • MCP Servers: Tools that provide capabilities to those clients (like MemoryPlugin for memory, file access tools, web search, etc.)
Think of it like this: The MCP Client is your AI chat app, and MCP Servers are plugins that give your AI new abilities. MemoryPlugin is one such server that adds memory capabilities.

​
Setup Requirements

MCP setup is currently more technical and requires some developer knowledge. We’re working on making this easier.

​
Prerequisites

  1. Node.js - Required to run the MCP server. Download from nodejs.org
  2. An MCP Client - Such as Claude Desktop, Cursor, Windsurf, or another supported application
  3. MemoryPlugin Account - To get your authentication token

​
How to Set Up

MCP servers are not “installed” like traditional software. Instead, you configure your MCP client to run the MemoryPlugin server when needed.
1

Get Your Auth Token

Sign in to the MemoryPlugin Dashboard and copy your authentication token from Settings
2

Configure Your MCP Client

Add the MemoryPlugin server configuration to your MCP client’s settings file (see example below)
3

Start Using

The AI will automatically use MemoryPlugin tools when appropriate
Account email independence: Your MemoryPlugin sign‑in email does not need to match the email you use on ChatGPT, Claude, TypingMind, or any other tool. Access and permissions are tied to your MemoryPlugin account (and API key when applicable), not third‑party logins.
For detailed setup instructions specific to your MCP client:

​
Supported MCP Clients

Claude Code

Anthropic’s official CLI tool

Cursor

AI-powered code editor

Windsurf

AI development environment

Cline

AI assistant for developers

Sage

AI assistant application

Roo-Code

AI coding assistant

VS Code Copilot

GitHub Copilot Chat in VS Code

And many more...

The list is growing every day

​
Configuration Example

Each MCP client has its own configuration format, but they all work similarly. Here’s an example for Claude Desktop: 
{
  "mcpServers": {
    "memoryplugin": {
      "command": "npx",
      "args": ["@memoryplugin/mcp-server"],
      "env": {
        "MEMORY_PLUGIN_TOKEN": "your-auth-token-here"
      }
    }
  }
}
This configuration tells your MCP client to run npx @memoryplugin/mcp-server when needed, which downloads and executes the MemoryPlugin server automatically. No installation required!

​
Available Tools

The MCP server provides tools organized by feature area. Tool descriptions are designed to help AI understand when and how to use each tool effectively.

​
Memory Tools

ToolDescription
store_memorySave information for future recall. AI is encouraged to proactively save preferences, decisions, and important context.
get_memories_and_bucketsRetrieve saved memories, optionally filtered by bucket. Also returns available buckets.
search_memoriesSemantic search across memories. Returns results ranked by relevance.
list_bucketsList available memory buckets.
create_bucketCreate a new bucket to organize memories.

​
Smart Memory Tools

For buckets with Smart Memory enabled:
ToolDescription
list_bucket_categoriesGet AI-generated categories for a bucket, including summaries and topic information.
list_category_memoriesLoad all memories within a specific category.

​
Chat History Tools

Search and retrieve from imported AI conversations:
ToolDescription
recall_chat_historySearch past conversations and get synthesized context. Supports parallel queries for complex topics.
get_conversation_summaryGet details of a specific conversation—full transcript for short ones, AI summary for long ones.
get_full_conversationRetrieve the complete transcript of a past conversation.

​
File Tools

Query uploaded documents:
ToolDescription
search_uploaded_filesSearch documents in your MemoryPlugin file buckets. Returns relevant passages with file and page info.

​
Tool Descriptions

The MCP server includes detailed tool descriptions that help AI understand:
  • When to use each tool (proactive guidance)
  • How to use parameters effectively
  • Which tool to choose for different situations
For example, store_memory encourages AI to proactively save useful information, while recall_chat_history explains how to use parallel queries for complex topics.

​
Features Available via MCP

When using MemoryPlugin through MCP, you get:
  • Memories — Store and retrieve information across conversations
  • Buckets — Organize memories into different contexts
  • Smart Memory — Access AI-organized categories and summaries
  • Chat History — Search your imported AI conversations
  • File Search — Query uploaded documents
  • Cross-Platform Sync — Same data across all your tools

​
Troubleshooting

Make sure Node.js is installed and available in your PATH. Test by running node --version in your terminal. You should see a version number like v20.10.0.
Verify your auth token is correct and copied completely from the dashboard. The token should be a long string of characters.
  1. Check your MCP client’s configuration file for typos
  2. Ensure the configuration is in the correct location for your client
  3. Try running npx @memoryplugin/mcp-server directly in terminal to test if it works
Restart your MCP client after adding the configuration. Some clients need a full restart to detect new servers.

​
Next Steps

Memory Buckets

Organize your memories into separate contexts

Smart Memory

Enable AI-powered memory organization

File Buckets

Upload documents to query via MCP

Remote MCP Server

Use MCP without local setup