In your PostgreSQL instance:

Skip to content

You signed in with another tab or window. Reload
to refresh your session. You signed out in another tab or window. Reload
to refresh your session. You switched accounts on another tab or window. Reload
to refresh your session. Dismiss alert

sdimitrov / mcp-memory Public

• Notifications
  You must be signed in to change notification settings

• Fork 0

• Star 2

MCP Memory Server with PostgreSQL and pgvector for long-term memory capabilities

2 stars
0 forks
Branches
Tags
Activity

Star

Notifications
You must be signed in to change notification settings

sdimitrov/mcp-memory

main

1 Branch
0 Tags

Go to file

Code

Folders and files

| Name | | Name | Last commit message | Last commit date |
| --- | --- | --- | --- |
| Latest commit
-------------


sdimitrov

cleanup

Mar 16, 2025

d6bcc4a
 · Mar 16, 2025

History
-------

2 Commits

| | |
| docs | | docs | Initial commit for MCP Memory Server | Mar 16, 2025 |
| migrations | | migrations | Initial commit for MCP Memory Server | Mar 16, 2025 |
| src | | src | cleanup | Mar 16, 2025 |
| .env.sample | | .env.sample | cleanup | Mar 16, 2025 |
| .gitignore | | .gitignore | Initial commit for MCP Memory Server | Mar 16, 2025 |
| CLAUDE.md | | CLAUDE.md | Initial commit for MCP Memory Server | Mar 16, 2025 |
| README.md | | README.md | Initial commit for MCP Memory Server | Mar 16, 2025 |
| package-lock.json | | package-lock.json | Initial commit for MCP Memory Server | Mar 16, 2025 |
| package.json | | package.json | Initial commit for MCP Memory Server | Mar 16, 2025 |
| View all files | | |

Repository files navigation

MCP Memory Server

This server implements long-term memory capabilities for AI assistants using mem0 principles, powered by PostgreSQL with pgvector for efficient vector similarity search.

Features

• PostgreSQL with pgvector for vector similarity search
• Automatic embedding generation using BERT
• RESTful API for memory operations
• Semantic search capabilities
• Support for different types of memories (learnings, experiences, etc.)
• Tag-based memory retrieval
• Confidence scoring for memories
• Server-Sent Events (SSE) for real-time updates
• Cursor MCP protocol compatible

Prerequisites

1. PostgreSQL 14+ with pgvector extension installed:

# In your PostgreSQL instance:
CREATE EXTENSION vector;

1. Node.js 16+

Setup

1. Install dependencies:

npm install

1. Configure environment variables: Copy .env.sample to .env and adjust the values:

cp .env.sample .env

Example .env configurations:

# With username/password
DATABASE_URL="postgresql://username:password@localhost:5432/mcp_memory"
PORT=3333

# Local development with peer authentication
DATABASE_URL="postgresql:///mcp_memory"
PORT=3333

1. Initialize the database:

npm run prisma:migrate

1. Start the server:

npm start

For development with auto-reload:

npm run dev

Using with Cursor

Adding the MCP Server in Cursor

To add the memory server to Cursor, you need to modify your MCP configuration file located at ~/.cursor/mcp.json. Add the following configuration to the mcpServers object:

{
  "mcpServers": {
    "memory": {
      "command": "node",
      "args": [\
        "/path/to/your/memory/src/server.js"\
      ]
    }
  }
}

Replace /path/to/your/memory with the actual path to your memory server installation.

For example, if you cloned the repository to /Users/username/workspace/memory, your configuration would look like:

{
  "mcpServers": {
    "memory": {
      "command": "node",
      "args": [\
        "/Users/username/workspace/memory/src/server.js"\
      ]
    }
  }
}

The server will be automatically started by Cursor when needed. You can verify it's working by:

1. Opening Cursor
2. The memory server will be started automatically when Cursor launches
3. You can check the server status by visiting http://localhost:3333/mcp/v1/health

Available MCP Endpoints

SSE Connection

• Endpoint: GET /mcp/v1/sse
• Query Parameters:
  • subscribe: Comma-separated list of events to subscribe to (optional)
• Events:
  • connected: Sent on initial connection
  • memory.created: Sent when new memories are created
  • memory.updated: Sent when existing memories are updated

Memory Operations

1. Create Memory

POST /mcp/v1/memory
Content-Type: application/json

{
  "type": "learning",
  "content": {
    "topic": "Express.js",
    "details": "Express.js is a web application framework for Node.js"
  },
  "source": "documentation",
  "tags": ["nodejs", "web-framework"],
  "confidence": 0.95
}

1. Search Memories

GET /mcp/v1/memory/search?query=web+frameworks&type=learning&tags=nodejs

1. List Memories

GET /mcp/v1/memory?type=learning&tags=nodejs,web-framework

Health Check

GET /mcp/v1/health

Response Format

All API responses follow the standard MCP format:

{
  "status": "success",
  "data": {
    // Response data
  }
}

Or for errors:

{
  "status": "error",
  "error": "Error message"
}

Memory Schema

• id: Unique identifier
• type: Type of memory (learning, experience, etc.)
• content: Actual memory content (JSON)
• source: Where the memory came from
• embedding: Vector representation of the content (384 dimensions)
• tags: Array of relevant tags
• confidence: Confidence score (0-1)
• createdAt: When the memory was created
• updatedAt: When the memory was last updated

About

MCP Memory Server with PostgreSQL and pgvector for long-term memory capabilities

Resources

Readme

Activity

Stars

2 stars

Watchers

1 watching

Forks

0 forks

Report repository

Releases

No releases published

Packages 0

No packages published

Languages

• JavaScript 100.0%

You can’t perform that action at this time.