Supermemory MCP server

supermemory is a powerful API designed to integrate external knowledge into AI applications. It serves as a memory layer for your AI stack, providing semantic search and retrieval capabilities that enhance AI models with relevant context, helping to eliminate hallucinations by grounding outputs in trusted content.

Getting Started

Creating an Account

To start using supermemory:

1. Sign up at console.supermemory.ai
2. Create your API key
3. Begin adding and querying content

Installation

Install the supermemory SDK using npm:

npm install supermemory

Basic Usage

Setting Up the Client

Initialize the supermemory client with your API key:

import { supermemory } from 'supermemory';

const client = new supermemory({
  apiKey: 'YOUR_API_KEY',
});

Adding Content

You can add various types of content to your knowledge base:

// Add a webpage
await client.memory.create({
  content: "https://en.wikipedia.org/wiki/Artificial_intelligence",
  metadata: {
    source: "wikipedia",
    category: "AI"
  }
});

Querying Your Knowledge Base

Search for information using natural language queries:

const results = await client.search.create({
  q: "What are the ethical considerations in AI development?",
  limit: 5
});

Key Features

Content Management

• Universal Content Handling: Automatically process and index content from URLs, PDFs, text, and more
• Advanced Filtering: Organize and retrieve information using metadata, categories, and user partitioning

Search Capabilities

• Semantic Search: Find information based on meaning, not just keyword matching
• Query Enhancement: Rewriting and reranking for more relevant results

Use Cases

supermemory can be used for various applications:

• RAG (Retrieval Augmented Generation): Enhance LLM outputs with accurate data
• Knowledge Bases & Documentation: Create intelligent, searchable repositories
• Customer Support: Build chatbots with access to your support documentation
• Research Assistants: Query across papers, notes, and references

Additional Resources

For more detailed information and examples, visit:

• Quick Start Guide
• API Reference
• SDK Documentation
• Use Cases & Examples

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 "supermemory" '{"command":"npx","args":["-y","supermemory"]}'

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": {
        "supermemory": {
            "command": "npx",
            "args": [
                "-y",
                "supermemory"
            ]
        }
    }
}

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": {
        "supermemory": {
            "command": "npx",
            "args": [
                "-y",
                "supermemory"
            ]
        }
    }
}

3. Restart Claude Desktop for the changes to take effect