Set it up
-
Turn on Memory in your AI
In Claude: open Settings → Connectors and add Memory. In ChatGPT: Settings → Apps & Connectors.
-
Add it to your app once
Copy the short config below into your app. It just tells your AI where to find Memory.
-
Just ask
Tell it what you want in plain words — no special commands.
For example, say
“Remember that I prefer pnpm over npm, and I use Biome instead of Prettier for formatting”
Need the exact config? Show it +
Add to your client
{
"mcpServers": {
"memory": {
"command": "npx",
"args": ["-y", "@modelcontextprotocol/server-memory"]
}
}
}Paste into your client's MCP configuration file.
Ready-to-run prompts
If you ask, Memory does it. Copy one, paste it into Claude, Codex or ChatGPT, done. No setup.
Memory Remember your stack
If you ask
“Remember that on this project we use TypeScript, Next.js 15, and tRPC”
Then
Tell your AI your stack once and have it remember.
Memory Remember your collaborators
If you ask
“Remember that Alex is the backend lead and prefers async written updates over meetings”
Then
Keep notes about collaborators so context is preserved.
Memory Track ongoing task state
If you ask
“Remember that I finished the auth rewrite last week and am now starting on the billing module”
Then
Track where you left off on multi-session projects.
Good to know
- · Memory files live on disk — protect them the same way you protect any other local data
- · Conflicting memories accumulate — occasionally review and prune
- · If you share your MCP config, others may see or overwrite your memories
When to use
- ✓ You're tired of repeating the same context every session
- ✓ You want your AI to remember project-specific preferences
- ✓ You're building long-running agents that need state across sessions
- ✓ You want personalized interactions over time
When not to use
- × You want every conversation to start fresh with no memory
- × You work on highly sensitive data that shouldn't persist across sessions
- × You share the MCP setup with others — their memories will mix with yours
About
Imagine your AI remembering what you told it last week — 'I prefer TypeScript', 'the project lead is Sarah', 'we use Postgres not MySQL' — and applying it automatically. This server gives your AI a persistent memory store so it can remember facts, preferences, and context across conversations.
The official Memory MCP server lets AI assistants maintain persistent knowledge across conversations using an in-process knowledge graph. Store entities, relations, and observations — and your AI will remember them session to session.
Perfect for building AI assistants that get smarter over time by retaining user preferences, project context, and learned facts.
Workflows That Use Memory MCP
Go from a one-line topic to a researched, sourced first draft saved to disk — before your coffee is cold, every day.
Clear a backlog of open pull requests in one pass — Claude reviews each one to your standards and tells you which ones are safe to merge.
Turn a single idea or note into a 5–10 slide branded carousel in under 30 minutes — without leaving the chat with Claude.
Replace 30 minutes of scrolling email and Slack with one written brief that tells you what actually needs you today.
Persistent memory across chats, live library docs, and structured reasoning — so answers stop drifting.
Works With
Also Consider
FAQ
What does Memory MCP do? +
Imagine your AI remembering what you told it last week — 'I prefer TypeScript', 'the project lead is Sarah', 'we use Postgres not MySQL' — and applying it automatically. This server gives your AI a persistent memory store so it can remember facts, preferences, and context across conversations.
Do I need to know how to code? +
No. Turn it on in your AI's settings and ask in plain English — no terminal, no coding.
When should I use Memory MCP? +
Reach for it when you need to: You're tired of repeating the same context every session; You want your AI to remember project-specific preferences; You're building long-running agents that need state across sessions; You want personalized interactions over time.
When should I avoid Memory MCP? +
Skip it when: You want every conversation to start fresh with no memory; You work on highly sensitive data that shouldn't persist across sessions; You share the MCP setup with others — their memories will mix with yours.
How do I install Memory MCP? +
In Claude Code, run: claude mcp add memory -- npx -y @modelcontextprotocol/server-memory. Copy-paste configs for Claude Desktop, Cursor, and Windsurf are at the top of this page.
