MCP server · Notes
ShadowGraph MCP server
by LiLara-AI
Your AI remembers what it decided, what it rejected and why, so old choices can be revisited.

ShadowGraph is a memory tool for your AI that keeps track of decisions, not just conversations. It saves what was chosen, what was turned down, the reason, and the moment a choice should be looked at again. It is handy if you use an AI assistant on a long project and want it to remember why things were done a certain way.
What is an MCP server? The 30-second version
On its own, your AI can only chat with you and forgets most things once the session ends. An MCP server is a small helper program that gives your AI a new skill or a connection to something useful. This one connects your AI to ShadowGraph, a memory store that lives on your own computer. When you ask your AI about an old decision, it can look it up in ShadowGraph and give you the answer.
What this MCP server does
You ask your AI something like why a certain tool was picked for a project. The AI uses this helper to look inside your local ShadowGraph store. The store holds the decision, the alternatives that were rejected, the reasons, and any conditions that would make the choice worth revisiting. The AI then tells you what it found, or records a new decision for you. Everything stays on your machine, and nothing is sent to a cloud service.
Click to zoomWhat you can do with it
- Record a decision with the options you rejected and the reason
- Save a fact, like the deployment being single-user, that can trigger a rethink
- Ask what decisions should be reviewed again now
- Look up why something was decided in the past
- Note a failed attempt so the same mistake is not repeated
- Store preferences, goals and notes for a project
- Mark a review signal as seen so it stops piling up
What it gives back to you
You get back plain answers in the chat, like a short list of decisions that need a second look, or the reason a choice was made. When you record something, the AI confirms it was saved. When you ask a question, you get the matching decisions, facts or notes with their reasons. Nothing is hidden or summarized away without telling you.
Before you start
What you need
- Node.js 20 or newer on your computer
- The ShadowGraph program installed from GitHub (it is not on npm yet)
- An AI app that supports MCP, like Claude Code or Cursor
Good to know
It can change or delete stored records, and a hard purge cannot be undone, so be careful with cleanup commands.
Install it with your AI
Add ShadowGraph 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 ShadowGraph 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.
Who it's for
People who work with an AI assistant on long projects and want it to remember why decisions were made, not just what was said.





