MCP server · Notes
MemCore MCP server
Give your AI a shared long-term memory so it remembers decisions and corrections across every project.
MemCore is a small memory database that lives on your own computer. It stores the things worth keeping, like decisions, corrections, and notes about what you already tried, so your AI assistant can look them up later instead of starting from scratch. It is handy for anyone who works with AI coding assistants and is tired of re-explaining the same things.
What is an MCP server? The 30-second version
On its own, your AI can only chat with you and forgets everything when the conversation ends. An MCP server is a small helper program that gives your AI a new skill or a connection to something useful. This one connects your AI to MemCore, a memory store on your machine, so the AI can save notes and search them when you ask. That way, what you told one AI tool can be found by another, and by the same tool tomorrow.
What this MCP server does
You ask your AI something, like why a certain approach was dropped. The AI uses this helper to search your MemCore database. MemCore looks through the notes you or your AI saved before, across all your projects, and returns the matching entries with their dates and details. If nothing was ever written down, it says so honestly instead of making something up. You can also ask your AI to save a new note, and it will write it into the same shared store.
What you can do with it
- Search your saved notes in plain language across every project
- Save a new decision or correction so future sessions know about it
- List everything recorded for one project or one type of note
- See what was recently added or changed
- Browse all the scopes (project areas) you have notes for
- Archive a note you no longer need and restore it later
- Import notes from Markdown files you keep in a folder
Try asking your AI
- “Why did we drop the queue-based design”
- “What did we decide about the date format”
- “Save this: the API returns cents, not dollars”
- “Show me the recent notes for the payments project”
What it gives back to you
You get back the matching notes as text, with the project they belong to, the date, and a short highlighted snippet. If you asked for recent items, you get a lighter list of titles and dates. When nothing matches, you get an empty result, which means nobody ever wrote that down. If your AI saved a note, it confirms the write and logs who did it and when.
Before you start
What you need
- Python 3.11 or newer installed on your computer
- The MemCore files downloaded from GitHub (a git clone)
- An AI tool that supports MCP, like Claude Code or Codex CLI
Good to know
Your AI can add, change, or archive notes in your memory store, so it is worth checking what it saved before trusting it completely.
Install it with your AI
Add MemCore 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 MemCore 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 4,609 MCP servers here for you.
Who it's for
People who use AI coding assistants daily and want them to remember decisions and corrections across projects without repeating themselves.
