Home › Knowledge & Memory › memex

memex

Temporal engineering context for agents via MCP.

Python Local macOSWindowsLinux

★ 12 stars Last pushed 2026-09-21 License: MIT

View repository →

Connect

Review any command before running it. Package names and URLs come from the server's own registry entry.

Package (npm 0.9.0)

npx -y stifler-memex-mcp@0.9.0

Or add to your MCP client config:

{
  "mcpServers": {
    "memex": {
      "command": "npx",
      "args": [
        "-y",
        "stifler-memex-mcp@0.9.0"
      ],
      "env": {
        "NEO4J_URI": "<YOUR_VALUE>",
        "NEO4J_USER": "<YOUR_VALUE>",
        "NEO4J_PASSWORD": "<YOUR_VALUE>",
        "GEMINI_API_KEY": "<YOUR_VALUE>"
      }
    }
  }
}

NEO4J_URI required — Bolt URI of your Neo4j instance
NEO4J_USER required — Neo4j username
NEO4J_PASSWORD required secret — Neo4j password
GEMINI_API_KEY required secret — Google Gemini API key for entity extraction

This server takes extra arguments — see its repository.

Package (pypi 0.9.0)

uvx memex-mcp

Or add to your MCP client config:

{
  "mcpServers": {
    "memex": {
      "command": "uvx",
      "args": [
        "memex-mcp"
      ],
      "env": {
        "NEO4J_URI": "<YOUR_VALUE>",
        "NEO4J_USER": "<YOUR_VALUE>",
        "NEO4J_PASSWORD": "<YOUR_VALUE>",
        "GEMINI_API_KEY": "<YOUR_VALUE>"
      }
    }
  }
}