cortex-mcp

Persistent memory for AI coding assistants. Injects context from past sessions into every LLM request.

Install Command

npx -y cortex-mcp

Claude Desktop Config

{
  "mcpServers": {
    "cortex-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "cortex-mcp"
      ]
    }
  }
}

cortex-mcp is a community MCP server that connects AI assistants like Claude to persistent memory for ai coding assistants. injects context from past sessions into every llm request. It runs locally on your machine, keeping your data private and giving you full control over the connection. This makes it easy to query and manage your data without leaving your AI assistant.

About cortex-mcp

Overview

Persistent memory for AI coding assistants. Injects context from past sessions into every LLM request.

Topics

mcp, mcp-server, model-context-protocol, memory, persistent-memory, ai, llm, context, coding-assistant, cursor, claude, copilot, windsurf, cline, gemini, ai-memory, hallucination-detection, developer-tools, code-context, sqlite, embeddings

Who Should Use cortex-mcp?

1Run natural-language queries against your database without writing SQL
2Inspect schemas, tables, and relationships during development
3Automate data exports, migrations, and reporting tasks
4Let AI assistants answer questions directly from your live data

How to Install cortex-mcp

Before you start

You will need Node.js (v18 or later) installed on your machine — download it from nodejs.org if you haven't already.

1Open a terminal (Terminal on Mac, Command Prompt or PowerShell on Windows).
2Paste the install command above and press Enter — Node.js will download and run the server automatically.
3Add the server to your Claude Desktop config file (see the JSON snippet above) and restart Claude.

The Claude Desktop config snippet above can be copied and pasted directly into your claude_desktop_config.json file — no editing required.