MCP server · Notes

Ratary MCP server

Give your AI a lasting memory so it remembers your notes, decisions and project details between chats.

Notes For it and development Knowledge & Memory

Ratary is a memory helper for AI assistants. It stores things you tell your AI, like project notes, decisions and background, and hands them back later when they are useful. It is handy if you keep repeating the same context in ChatGPT, Claude or Cursor and want your AI to just remember it.

What is an MCP server? The 30-second version

On its own, your AI can only chat with what is in front of it, and it forgets everything once the conversation ends. An MCP server is a small helper program that gives your AI a new skill or a connection to another service. This one connects your AI to Ratary, a memory store, so it can save notes and look them up again. When you ask something, the AI quietly checks Ratary first and uses what it finds.

What this MCP server does

You tell your AI something worth keeping, like a decision or a project detail. The AI sends that to Ratary through this helper. Ratary saves it, links it to related notes, and keeps it in a database you control. Later, when you ask a question, the AI searches Ratary and pulls back only the parts that matter. You get an answer that already knows your history, without pasting old context again.

Flow diagram: you ask your AI “Remember this decision for the project”, the Ratary MCP server connects it to Ratary memory, and you get back answers that know your history.

Click to zoom

What you can do with it

Save notes, decisions and project background to a lasting memory
Search your saved memories by keyword or meaning
Pull the most relevant memories into the current chat
Link related memories together so context stays connected
Keep separate memories for different projects or teams
Run it on your own computer or server so you own the data

What it gives back to you

You get answers in the chat that already include your saved context. When you search, it gives back a short list of matching memories with their titles and a snippet. When you save something, it confirms the memory was stored. You can also ask for a summary of what it found.

Before you start

What you need

Node.js 24 installed on your computer
A database to store memories, such as Postgres (the default) or Cloudflare D1
A secret key and database address set in a small settings file
An API key that starts with aic_ once the server is running

Good to know

Ratary stores whatever you save, so avoid putting passwords, private keys or sensitive personal data into your memories.

Install it with your AI

Add Ratary MCP server to your AI, no technical skills needed

You don't install anything by hand. You copy one prompt, paste it into an AI that can work on your computer, and it checks, installs and connects the server for you, asking you when it needs something.

Sign in to get the install prompt

Members get a ready-made prompt that lets the Claude desktop app check Ratary MCP server, install it and connect it for them, step by step. You don't need any technical skills: you copy, paste and answer a few questions. Your connected AI can also find and install any of the 4,066 MCP servers here for you.