MemDx
Verified IntegrationClient Configuration
— Connect MemDx to Claude Desktop or Cursor in seconds{
"mcpServers": {
"memdx": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-memdx"
],
"env": {}
}
}
}~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows).System Overview
Provides a local, persistent AI memory layer within your IDE to store project context and decisions across sessions.
7/23/2026
Open Source
stdio / SSE RPC
Frequently Asked Questions
Architecture and operational details for MemDx
MemDx runs 100% locally on your machine using Docker (Qdrant for vectors, Ollama for models). All your project data and AI context remain on your device, ensuring complete privacy and control.
Related MCP Servers
Browse all servers →Empower AI assistants to generate and convert documents, manage templates, and automate document workflows efficiently.
Provides a multi-tenant, AI-native Content Delivery Network deployable on Cloudflare, featuring sub-100ms TTFB, AI agent controllability, and comprehensive accessibility.
Deploy a Model Context Protocol server on Cloudflare Workers without requiring authentication.