Persistent memory using a knowledge graph
The Memory MCP Server gives your AI assistant persistent memory using a local knowledge graph. Create entities, define relationships between them, and query the graph later. Information persists across conversations, letting your AI remember context, decisions, and preferences.
Is it safe?
No known CVEs for @modelcontextprotocol/server-memory.
No authentication — any process on your machine can connect to this server.
MIT. View license →
Last scanned 0 days ago.
Is it maintained?
Last commit 5 days ago. 82,845 GitHub stars. 98,160 weekly downloads.
Will it work with my client?
Transport: stdio. Works with claude-desktop, cursor, claude-code, windsurf.
How much context will it use?
5 tools. Estimated ~100 tokens of your context window (0.1% of 200K).
What if it doesn't work?
Common issues: JSON syntax errors in config, wrong Node.js version, npx cache. Setup guide covers troubleshooting. Or check GitHub issues for known problems.
{
"mcpServers": {
"memory": {
"args": [
"-y",
"@modelcontextprotocol/server-memory"
],
"command": "npx"
}
}
}Run this in your terminal to verify the server starts. Then let us know if it worked — your result helps other developers.
npx -y @modelcontextprotocol/server-memory 2>&1 | head -1 && echo "✓ Server started successfully"
After testing, let us know if it worked:
create_entitiesCreate new entities in the knowledge graph
create_relationsCreate relationships between entities
search_nodesSearch for nodes in the graph
open_nodesRead specific nodes
delete_entitiesRemove entities from the graph
Last scanned 1h ago
No known vulnerabilities.
Have you used this server?
Share your experience — it helps other developers decide.
Sign in to write a review.
Start a conversation
Ask a question, share a tip, or report an issue.
Sign in to join the discussion.