Norn MCP server

Norn

Persistent, visible memory for AI coding agents.

Live site · Releases · Quickstart · Connect your AI tool

Your AI forgets you every session. Norn is a local MCP server that remembers your decisions, preferences, and project context across every session and project, for Claude Code, Cursor, and any MCP client. Unlike most memory tools it is fully local and fully inspectable: a dashboard lets you see exactly what it stored and forget anything you do not want.

Quickstart

What you need: just Node.js 20 or newer — you don't install Norn separately, the command below fetches it automatically. Check with node --version; if it's missing or below v20, grab the LTS from nodejs.org.

Connect to Claude Code — one command, no clone:

claude mcp add norn -- npx -y @samad001z/norn-server

Or use the CLI in your terminal — run it on demand, or install the norn command:

npx @samad001z/norn-core list           # no install — npx fetches it each time
npm install -g @samad001z/norn-core     # or put the `norn` command on your PATH

Any other MCP client — add this to its MCP config:

{
  "mcpServers": {
    "norn": {
      "command": "npx",
      "args": ["-y", "@samad001z/norn-server"]
    }
  }
}

Restart your tool. Norn registers four tools: remember, recall, forget, list.

Optional — flag possible conflicts: add "env": { "NORNDETECTCONFLICTS": "1" }

to the config above and Norn will surface memories that might disagree, for you to

resolve in the dashboard. Off by default; it downloads a small extra model the first

time it finds a candidate, and it never changes your store on its own.

Not sure where that config goes? The Connect Norn to your AI tool

guide has exact, copy-paste setup for Claude Desktop, Cursor, Windsurf,

VS Code + GitHub Copilot, and Gemini CLI — plus a beginner "what you need" and

troubleshooting. (VS Code + Copilot uses a servers key instead of mcpServers.)

Verify it's connected: tell your assistant "Remember that I prefer pnpm over npm," then in a new chat ask "What package manager do I prefer?" — it should answer pnpm by calling Norn's recall tool.

The first remember or recall downloads a local embedding model

(all-MiniLM-L6-v2, ~25 MB) once, then runs fully offline.

Or run from source

git clone https://github.com/samad001z/Norn.git
cd Norn
npm install
npm run build -w @samad001z/norn-core && npm run build -w @samad001z/norn-server
claude mcp add norn -- node "$(pwd)/server/dist/index.js"

See it work

Memory survives across sessions, and recall is semantic: it matches meaning, not keywords.

Session 1

You: Remember that we deploy to production from the main branch on Vercel.

Claude calls remember("deploy to production from the main branch on Vercel", project: "acme")

Session 2, the next day, in a fresh context window

You: How do we ship to prod?

Claude calls recall("how do we ship to prod")

Norn returns "Deploy to production from the main branch on Vercel." even though the

query shares no keywords with the stored note.

Using memory: it's explicit, not automatic

Norn does not record your sessions. It is a memory store, not a logger — it never silently captures your prompts, code edits, or terminal commands. A memory exists only when the agent calls remember(), which happens in two ways:

Shortened. The full README is on GitHub.