Complete AI Training

MCP server · Notes

Central Memory MCP server

by MWGMorningwood

Lets your AI save and look up shared project notes, people, and links between them, kept in one place for your team.

Flow diagram: you ask your AI “Who works on the payments project?”, the Central Memory MCP server connects it to Team memory store, and you get back answers in your chat.

This is a memory server for your AI assistant. It keeps a shared set of notes about your project, like people, tools, and how they connect, in one central spot. It is handy if several people on a team want their AI helpers to work from the same project knowledge instead of each one remembering things on its own.

What is an MCP server? The 30-second version

On its own, your AI can only chat with you. 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 central memory store for your project, so it can look up and add notes there when you ask. Think of it as a shared notebook your AI is allowed to read and write in.

What this MCP server does

You ask your AI something about your project, like who is involved or how two things are related. The AI uses this helper to talk to the central memory store. The store keeps two lists: one for entities (people, tools, ideas) and one for relations (how those entities connect). The helper fetches what you asked for and hands it back to your AI, which then explains it to you in the chat. If you ask it to add or update something, it writes that into the same store so your teammates' AI helpers can see it too.

Flow diagram: you ask your AI “Who works on the payments project?”, the Central Memory MCP server connects it to Team memory store, and you get back answers in your chat. Click to zoom

What you can do with it

  • Read the full list of entities saved for a workspace
  • Add a new entity or update an existing one by name
  • Create or update a relation between two entities
  • List all relations that start from a specific entity
  • Check that the memory service is up and ready
  • Keep each team's notes separate using a workspace name

Try asking your AI

  • “Read the graph for the workspace called project-alpha and list every entity you find.”
  • “Add an entity named Sarah Chen with the observation that she leads the backend team.”
  • “Create a relation from Sarah Chen to the Payments API with the label owns.”
  • “Show me all relations that start from the entity called Payments API.”

What it gives back to you

You get back lists and short answers in the chat. For example, reading the graph gives you the entities saved for that workspace, and asking about relations gives you the links coming out of one entity. When you add or update something, the AI tells you it was saved. The notes themselves live in the central store, not in your chat history.

Before you start

What you need

  • The Central Memory MCP server running somewhere your AI can reach (the team hosts it on Azure Functions)
  • A workspace name agreed with your team so everyone reads and writes the same notes
  • An MCP-capable AI client, like the Claude desktop app, pointed at this server

Good to know

It can add and change the shared notes your whole team reads, so be careful about what you ask it to save or overwrite.

Install it with your AI

Add Central 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 Central 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

Software teams and small groups who want several people's AI assistants to share the same project notes and connections.