Lets an AI assistant find, run and build workflows on your n8n instance.
Memory MCP Server
MCP server by Model Context Protocol
Memory MCP Server at a glance
Memory MCP Server is an official MCP server from Model Context Protocol. It gives an AI assistant persistent memory stored as a local knowledge graph of entities and relations.
- Connects to
- Memory and automation
- Hosting
- Local · stdio
- Sign-in
- None
- Price
- Free
- Works with
- Claude Desktop, VS Code
- Best for
- Anyone wanting simple local memory for assistants
- Checked
- October 3, 2026 on official sources
How to install Memory MCP Server
Add the command below as a new MCP server in your AI app’s settings or MCP config file. Sign-in: None.
npx -y @modelcontextprotocol/server-memoryWhat Memory MCP Server can do
It saves people, projects and facts as entities with observations and links between them. The data lives in a local JSONL file so the assistant can recall it in later chats.
Best for: anyone wanting simple local memory for assistants
Pros
- No account or API key needed
- Data stays in a local file
- Small and easy to inspect
Cons
- No semantic or vector search
- Single local file does not sync across devices
Memory MCP Server FAQ
Is Memory MCP Server free?
Yes. It is open source under MIT and runs on your own machine.
How do I connect Memory MCP Server?
Add it to your MCP client config with the command npx -y @modelcontextprotocol/server-memory.
What can Memory MCP Server do?
It creates entities and relations, adds observations, searches nodes and reads back the whole knowledge graph.