Complete AI Training

MCP server · Notes

Cortex Memory MCP server

by cdeust

Give your AI a long-term memory for your project, so it remembers decisions and fixes between sessions.

Flow diagram: you ask your AI “What did we decide about session state last week?”, on your own computer the Cortex Memory MCP server works with your computer, and you get back relevant memories in chat.

Cortex is a memory helper for AI coding agents. It lets your AI keep track of decisions, fixes and project context between sessions, and it runs on your own machine. It is handy for developers who use Claude Code or Codex and are tired of repeating the same background every time.

What is an MCP server? The 30-second version

On its own, your AI can only chat about what is in front of it. An MCP server is a small helper program that gives your AI a new skill or a connection to an app or service. This one connects your AI to a local memory store, so it can save and look up project notes for you. When you ask about something from an earlier session, the AI uses this helper to find it.

What this MCP server does

You ask your AI a question or give it a task. The AI uses this helper to check your local memory store for related decisions, fixes or context. The helper searches what was saved before and hands back the most relevant pieces. The AI then uses that to answer you or continue the work. It can also save new memories as you go, so the next session starts with the right background.

Flow diagram: you ask your AI “What did we decide about session state last week?”, on your own computer the Cortex Memory MCP server works with your computer, and you get back relevant memories in chat. Click to zoom

What you can do with it

  • Remember project decisions between sessions
  • Recall a fix from an earlier debugging session
  • Save a note about how something works
  • Check whether a memory is still accurate
  • Correct an old memory without losing the history
  • Keep a self-curating project wiki
  • Share memory between Claude Code and Codex

Try asking your AI

  • “What did we decide about session state last week?”
  • “Have we seen this login timeout problem before?”
  • “Save a note that we use Redis for session TTL.”
  • “Show me the decisions we made about authentication.”

What it gives back to you

You get answers in the chat that include the relevant memories the AI found. It can also show you a list of related notes, with short labels about how trustworthy each one is. When it saves something, you get a small confirmation. When it corrects a memory, the old one is kept but marked as replaced.

Before you start

What you need

  • Claude Code, Claude Desktop, Codex, or another local MCP host
  • Node.js or Python, depending on how you install it
  • No account or API key needed for the default local setup

Good to know

It reads and writes files in a local memory store on your machine, so treat that store as private project data.

Install it with your AI

Add Cortex Memory 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 Cortex Memory 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.

Sign in Become a member

Who it's for

Developers and technical teams who use AI coding agents and want them to remember project context across sessions.