Complete AI Training

MCP server · Notes

SAIHM Memory MCP server

by SAIHM-Admin

Give your AI a private, encrypted memory it can remember, recall, share and erase on request.

Flow diagram: you ask your AI “Remember that I take my coffee black”, the SAIHM Memory MCP server connects it to Your memory keeper, and you get back your note is saved.

This is a helper that gives your AI assistant a long-term memory it can keep between chats. You tell it something once, and later it can bring that fact back when you ask. It is handy if you are tired of re-explaining your projects and preferences every time you start a new conversation.

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 a service. This one connects your AI to a SAIHM memory service, so it can store and look up things for you. Think of it as giving your assistant a notebook it can write in and read from when you ask.

What this MCP server does

You ask your AI to remember something, like a preference or a project detail. The AI calls this helper, and the helper sends that note to a SAIHM operator, which is the service that keeps your memories. Later, when you ask what it knows about you, the AI calls the helper again and the operator sends the memory back. The helper itself does not store anything or do any scrambling; it just passes messages between your AI and the operator you point it at.

Flow diagram: you ask your AI “Remember that I take my coffee black”, the SAIHM Memory MCP server connects it to Your memory keeper, and you get back your note is saved. Click to zoom

What you can do with it

  • Remember a fact, preference or decision so your AI keeps it
  • Recall what your AI already knows about you
  • Forget a memory for good, with a proper erasure
  • Share a single memory with another agent or person
  • Take back a share you gave earlier
  • Check your memory stats and storage tier
  • Propose or vote on protocol changes, if your operator has turned that on

Try asking your AI

  • “Remember that I take my coffee black and that I'm building a Rust CLI called ferry.”
  • “What do you know about me?”
  • “Forget everything you stored about my old project.”
  • “Share my note about the ferry project with my teammate's agent.”

What it gives back to you

When you ask it to remember something, it usually just confirms the note was stored. When you ask it to recall, it comes back with the facts it found, written out in the chat as plain sentences or a short list. Forget and share give you a simple confirmation that the action went through. Status gives you a small dashboard of numbers about your memory store.

Before you start

What you need

  • A SAIHM operator endpoint URL, which is the web address of the memory service you run or subscribe to
  • A token from that operator, which works like a password for the service
  • Node.js installed on your computer so npx can run the helper
  • A custodial operator, meaning one that does the scrambling on its side; the hosted saihm.net service is not one of these

Good to know

The forget tool erases a memory permanently and cannot be undone, so be sure before you ask for it.

Install it with your AI

Add SAIHM 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 SAIHM 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

People who use an AI assistant every day and want it to remember their projects and preferences without repeating themselves.