Complete AI Training

MCP server · Notes

passbaton MCP server

by leesgit

Your AI remembers what you did last session, so you never re-explain your project again.

Flow diagram: you ask your AI “What was I working on last time in this project?”, on your own computer the passbaton MCP server works with your own computer, and you get back A short summary in your chat.

passbaton is a small helper that keeps notes about your work and hands them back to your AI at the start of every new session. It works with Claude Code, Codex CLI and Gemini CLI, and it keeps everything on your own computer. It is handy if you are tired of typing the same project background over and over.

What is an MCP server? The 30-second version

On its own, your AI can only chat with you in the moment. It forgets everything when the session ends. An MCP server is a small helper program that gives your AI a new skill or a connection to something outside the chat. passbaton is that helper here: it watches your coding sessions, saves the important bits to a local file, and quietly feeds them back to your AI next time you start working.

What this MCP server does

You install passbaton once, and it hooks into your AI tool in the background. When you start a new session, it looks up what you worked on before and shows a short summary at the top. While you work, it notices decisions, errors and fixes, and saves them. If your session gets compressed to save space, passbaton writes a handover so nothing important is lost. When you close the session, it reads the conversation and pulls out commits, decisions and error-fix pairs for next time.

Flow diagram: you ask your AI “What was I working on last time in this project?”, on your own computer the passbaton MCP server works with your own computer, and you get back A short summary in your chat. Click to zoom

What you can do with it

  • See a summary of your last sessions the moment you open a new one
  • Stop retyping project background and past decisions
  • Search your past work in English, Korean or Japanese
  • Get past solutions suggested when the same error shows up again
  • Keep a list of tasks with priorities across sessions
  • Share one memory across Claude Code, Codex CLI and Gemini CLI
  • Keep everything on your own machine with no cloud and no API cost

Try asking your AI

  • “What was I working on last time in this project?”
  • “Have we seen this build error before, and how did we fix it?”
  • “What decisions did we make about the auth system?”
  • “Show me my open tasks for this project”

What it gives back to you

You get short summaries in the chat: what you did recently, which files were active, decisions you made, and any past solutions to errors. It can also return search results from your saved memories and a list of tasks. Everything appears as plain text inside the conversation, so you can read it like a note from a colleague.

Before you start

What you need

  • Node.js 22 or newer installed on your computer
  • Claude Code, Codex CLI or Gemini CLI set up and working
  • A terminal where you can run one install command

Good to know

It reads your session transcripts and saves notes about your work to a local database, so keep that file out of git if your project has secrets in the conversation.

Install it with your AI

Add passbaton 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 passbaton 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 folks who use AI coding tools daily and are tired of repeating project context every session.