Cortex MCP Server

Local-first knowledge graph that watches your project files, extracts entities and relationships via LLMs, and lets you query across projects in

Local serverstdioTypeScript

What is the Cortex MCP server?

Cortex MCP server exists for a simple reason — assistants are far more useful when they can act on Cortex directly instead of describing what you should do. Local-first knowledge graph that watches your project files, extracts entities and relationships via LLMs, and lets you query across projects in natural language.

What you get

You work on multiple projects. Decisions, patterns, and context are scattered across hundreds of files. You forget what you decided three months ago. You re-solve problems you already solved in another repo.

Built by GZOO — an AI-powered business automation platform.

Setting it up

Installation goes through your MCP client rather than a global install: point it at @gzoo/cortex on npm and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.

Configuration and credentials

You will need 3 environment variables: CORTEX_SERVER_AUTH_TOKEN, OPENAI_API_KEY, CORTEX_TOKEN. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.

  • Node.js 20+ - LLM API key for cloud modes — Anthropic, Google Gemini, DeepSeek, Groq, or any OpenAI-compatible provider - Ollama — only for hybrid, local-first, or local-only modes (install)

Before you rely on it

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the cortex mcp server does with a few real requests.

Choosing this one

Among the knowledge and memory options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. It is maintained by gzoonet; worth a glance at recent repository activity before you build anything load-bearing on it.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

How to install the Cortex MCP server

{
  "mcpServers": {
    "cortex": {
      "command": "npx",
      "args": ["-y", "@gzoo/cortex"],
      "env": {
        "CORTEX_SERVER_AUTH_TOKEN": "your-value",
        "OPENAI_API_KEY": "your-value",
        "CORTEX_TOKEN": "your-value"
      }
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

  • Node.js 20+ - LLM API key for cloud modes — Anthropic, Google Gemini, DeepSeek, Groq, or any OpenAI-compatible provider - Ollama — only for hybrid, local-first, or local-only modes (install)
VariableDescriptionRequired
CORTEX_SERVER_AUTH_TOKENCredential the server authenticates with.Yes
OPENAI_API_KEYCredential the server authenticates with.Yes
CORTEX_TOKENCredential the server authenticates with.Yes

Frequently asked questions

It connects Cortex to MCP-compatible AI assistants such as Claude and Cursor. Instead of copying data back and forth by hand, the assistant works with Cortex directly.