MCP Memory
@Puliczek
About MCP Memory
🔥🖥️ MCP Memory is a MCP Server that gives MCP Clients (Cursor, Claude, Windsurf and more) the ability to remember information about users (preferences, behaviors) across conversations.
Basic information
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"mcp-memory-puliczek": {
"command": "npx",
"args": [
"wrangler",
"vectorize",
"create",
"mcp-memory-vectorize",
"--dimensions",
"1024",
"--metric",
"cosine"
]
}
}
}Tools
No tools detected
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Overview
What is MCP Memory?
MCP Memory is an MCP server that gives MCP clients (Cursor, Claude, Windsurf, and more) the ability to remember information about users across conversations. It uses vector search technology to find relevant memories based on meaning, not just keywords, and is built with Cloudflare Workers, D1, Vectorize, Durable Objects, Workers AI, and Agents.
How to use MCP Memory?
You can deploy your own instance via a one‑click Cloudflare button, by using the repository template, or by creating with the Cloudflare CLI. After deployment, configure the required Vectorize index (dimensions 1024, metric cosine) and install dependencies. The server can also be run locally with wrangler dev for development.
Key features of MCP Memory
- Semantic memory retrieval using vector embeddings
- Built on Cloudflare’s free‑tier infrastructure
- Isolated namespaces per user for data separation
- Built‑in rate limiting (100 req/min, configurable)
- Supports MCP clients like Cursor, Claude, Windsurf
- Open‑source, self‑hostable on Cloudflare
Use cases of MCP Memory
- Store and recall user preferences and behaviors across conversations
- Maintain a persistent knowledge base of technical documentation or procedures
- Track user interactions and common usage patterns
- Keep project notes, decisions, and updates accessible via semantic search
FAQ from MCP Memory
Can I use memory.mcpgenerator.com to store my memories?
Yes, you can use the hosted service for free, but availability is not guaranteed.
Can I host my own instance?
Yes, you can host your own instance for free on Cloudflare using Workers, Vectorize, D1 Database, and Workers AI.
Can I run it locally?
Yes, you can run MCP Memory locally for development with wrangler dev, though some features require a connection to Cloudflare’s services.
Can I use different hosting?
No, MCP Memory is specifically designed for Cloudflare’s infrastructure.
Can I use it for more than one person?
Yes, each user gets their own isolated memory space, making it suitable for multi‑user applications.
Can I store things other than memories?
Yes, MCP Memory can store any text‑based information, such as knowledge bases, user behaviors, and project notes.
More Memory & Knowledge MCP servers
Jupyter Notebook MCP Server (for Cursor)
jbenoModel Context Protocol (MCP) server designed to allow AI agents within Cursor to interact with Jupyter Notebook (.ipynb) files
Mcp Knowledge Graph
shanehollomanMCP server enabling persistent memory for Claude through a local knowledge graph - fork focused on local development
Memory Bank MCP Server
alioshrA Model Context Protocol (MCP) server implementation for remote memory bank management, inspired by Cline Memory Bank.
Memory
modelcontextprotocolModel Context Protocol Servers
JupyterMCP - Jupyter Notebook Model Context Protocol Integration
jjsantos01A Model Context Protocol (MCP) for Jupyter Notebook
Comments