MCP server · Notes

Agent Memory Bridge MCP server

Lets your coding AI remember project decisions and reasons across separate chat sessions.

Notes For it and development Knowledge & Memory

Agent Memory Bridge is a small helper that gives your coding assistant a memory for the important decisions your team makes. Instead of explaining the same rule again in every new chat, you teach it once and it comes back later. It is handy for developers and anyone who works with a coding AI on the same project for weeks.

What is an MCP server? The 30-second version

On its own, your AI can only chat with you. It forgets everything the moment you close the window. An MCP server is a small helper program that gives your AI a new skill or a connection to something else. This one connects your AI to a local memory store for your project, so it can save a decision you tell it and bring that decision back in a later session.

What this MCP server does

You install this helper once on your computer and connect it to the coding assistant you already use. When you tell your assistant something worth remembering, like a rule about merging code, the assistant uses this helper to save it. The helper writes it into a small local database on your machine. Next time you open a fresh session and ask a related question, the assistant asks the helper, gets the saved decision back, and answers you with it.

Flow diagram: you ask your AI “What is required before we merge a pull request?”, on your own computer the Agent Memory Bridge MCP server works with your own computer, and you get back your saved decision, in plain words.

Click to zoom

What you can do with it

Save a project decision and the reason behind it
Recall saved decisions when you ask a related question in a new session
Browse what the helper currently knows about your project
Correct or replace a decision that has changed
Mark a decision as no longer in use
Export what has been saved
Track a run of work and its events

Try asking your AI

“Remember that we merge pull requests only after CI is green on the target branch, because broken main blocked two releases this month.”
“What is required before we merge a pull request?”
“Show me everything you remember about this project.”
“That Redis decision is out of date, we stayed local-first instead.”

What it gives back to you

You get answers in the chat, written in normal sentences. When you ask a question, the assistant replies with the saved decision and the reason it was saved. When you ask it to browse or show what it knows, you get a list of the saved items. Nothing is shown as raw data unless you ask for it.

Before you start

What you need

Python 3.11 or newer
Git installed on your computer
A coding assistant that can launch a local MCP server, such as Codex, Claude Code, Cursor, or Cline

Good to know

It can save, change, and remove items in your project memory, so review what your assistant stores before you rely on it.

Install it with your AI

Add Agent Memory Bridge 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 Agent Memory Bridge 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.