Complete AI Training

MCP server · Notes

Memkin MCP server

by AndreLYL

Let your AI remember your Feishu chats and coding sessions, stored privately on your own computer.

Flow diagram: you ask your AI “What did I discuss with Zhang last week?”, on your own computer the Memkin MCP server works with your own computer, and you get back answer in your chat.

Memkin is a personal memory helper that runs on your own computer. It reads your Feishu (Lark) messages, emails, calendars, docs and tasks, plus your AI coding sessions, and turns them into a private knowledge graph. It is handy if you keep losing context between chats and want your AI to remember people, projects and decisions for you.

What is an MCP server? The 30-second version

On its own, your AI can only chat about what you paste into the window. It forgets everything the moment you close it. An MCP server is a small helper program that gives your AI a new skill or a connection to an app, and here it connects your AI to your own Memkin memory. Once connected, your AI can look things up in your past Feishu chats and coding sessions, and write new notes back, all without leaving the chat.

What this MCP server does

You ask your AI a question in plain words, like what you discussed with a colleague last week. Your AI passes that question to Memkin through this helper. Memkin searches the knowledge graph it built from your Feishu messages, emails, calendar, docs and AI coding sessions. It finds the matching people, projects, decisions and tasks, and hands a summary back. Your AI then shows you the answer in the chat, with references you can trace back to the original message.

Flow diagram: you ask your AI “What did I discuss with Zhang last week?”, on your own computer the Memkin MCP server works with your own computer, and you get back answer in your chat. Click to zoom

What you can do with it

  • Ask what you talked about with a specific person last week
  • Get a daily report pulled from chats, emails, meetings and your calendar
  • Check the current status of a project, including decisions and open tasks
  • Prepare for a meeting with someone by reviewing past interactions
  • Search your own memory for a topic, decision or task
  • Save new notes or findings back into your memory graph
  • Export your memory as Markdown files you can open in Obsidian

Try asking your AI

  • “What did I discuss with Zhang last week?”
  • “Generate today's daily report.”
  • “What is the current status of the memkin project?”
  • “Prepare me for tomorrow's renewal meeting with Mr. Zhang.”

What it gives back to you

You get answers in the chat, written in normal sentences. They often come with small numbered references like [1] that point back to the original message or session. For a daily report you get a structured summary split into sections. For a project question you get decisions, open tasks and a short timeline.

Before you start

What you need

  • Node.js version 18 or newer (the install script can set this up for you)
  • A Feishu (Lark) account if you want it to read your chats and calendar
  • An LLM API key, entered during the setup wizard, so it can extract signals from your messages
  • An AI client that supports MCP, such as Claude Code, Claude Desktop, Cursor, Codex or Windsurf

Good to know

It reads your private Feishu messages, emails, calendar and coding sessions, so only run it on a computer you trust, and remember that it can also write new notes back into your memory.

Install it with your AI

Add Memkin 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 Memkin 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 work heavily in Feishu or Lark and use AI coding tools, and who want a private memory of their work that stays on their own machine.