Memorizer MCP server

Memorizer is a .NET-based service that enables AI agents to store, retrieve, and search through memories using vector embeddings. It provides efficient similarity search capabilities through PostgreSQL with the pgvector extension, allowing AI agents to maintain persistent memory and build knowledge graphs.

Installation Options

Quick Start with Docker

The simplest way to get started is using the pre-built Docker image:

docker-compose up -d

This command will:

• Download the latest Memorizer image from Docker Hub
• Start PostgreSQL with pgvector (port 5432)
• Start PgAdmin (port 5050)
• Start Ollama (port 11434)
• Start Memorizer API (port 5000)

Once running, you can access the Memorizer Web UI at http://localhost:5000/ui.

Building from Source

If you prefer to build and run from source:

Prerequisites

• Docker and Docker Compose
• .NET 9.0 SDK

Steps

1. Build and publish the local container:

# From solution root directory
dotnet publish -c Release /t:PublishContainer

2. Start the infrastructure and application:

docker-compose -f docker-compose.local.yml up -d

Using Memorizer

MCP Configuration

To connect Memorizer with any MCP-compatible client, add the following to your configuration file (e.g., mcp.json):

{
  "memorizer": {
    "url": "http://localhost:5000/sse"
  }
}

Web UI

Memorizer includes a web-based user interface for managing memories through your browser at http://localhost:5000/ui/.

The Web UI provides:

• Memory management (create, view, edit, delete)
• Search and filtering by semantic similarity and tags
• Statistics dashboard
• MCP configuration information

Using with LLMs

For optimal integration with language models, include this system prompt in your AI agent configuration:

You have access to a long-term memory system via the Model Context Protocol (MCP) at the endpoint memorizer. Use the following tools:

• store: Store a new memory. Parameters: type, content (markdown), source, tags, confidence, relatedTo (optional, memory ID), relationshipType (optional).
• search: Search for similar memories. Parameters: query, limit, minSimilarity, filterTags.
• get: Retrieve a memory by ID. Parameter: id.
• getMany: Retrieve multiple memories by their IDs. Parameter: ids (list of IDs).
• delete: Delete a memory by ID. Parameter: id.
• createRelationship: Create a relationship between two memories. Parameters: fromId, toId, type.

This system prompt will improve how effectively your LLM uses Memorizer for persistent memory management.

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 "memorizer" '{"url":"http://localhost:5000/sse"}'

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": {
        "memorizer": {
            "url": "http://localhost:5000/sse"
        }
    }
}

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": {
        "memorizer": {
            "url": "http://localhost:5000/sse"
        }
    }
}

3. Restart Claude Desktop for the changes to take effect