cortexapps/cortex-mcp

Cortex MCP Overview

[!NOTE] Research Preview

Not seeing the results you expect? This is an early version of the Cortex MCP. Please send feedback and bug reports to Cortex Customer Engineering.

Cortex MCP is a Model Context Protocol server that provides access to the Cortex API. It uses relevant context from your workspace, ensuring awareness of your system’s structure when answering your questions.

You can query information in natural language, powering faster decisions and efficient processes. For example:

• Who is the right person to handle an incident with backend-server?
• Show me the services that belong to the platform engineering team
• We’re having an incident with backend-server, give me a summary of information to help handle the incident

Requirements

Before getting started, you’ll need:

• MCP Client: Claude Desktop or other MCP-compatible client
• Cortex Personal Access Token: Create a token in your Cortex workspace settings.

Installation

[!NOTE] Docker Required

Make sure Docker is installed and running on your system before proceeding with the installation.

Then configure your MCP client. We’ve tested this with Claude Desktop, and Cursor, but it should work with any MCP-compatible client.

If you are a self-managed Cortex customer, you must also set CORTEX_API_BASE_URL=https:// alongside the CORTEX_API_TOKEN variable. See the docs for an example configuration.

Claude Desktop

{
  "mcpServers": {
    "cortex": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "--env",
        "CORTEX_API_TOKEN=YOUR_API_TOKEN_HERE",
        "ghcr.io/cortexapps/cortex-mcp:latest"
      ]
    }
  }
}

Claude Code

Use the following command to add Cortex MCP to Claude Code:

claude mcp add-json "cortex" '{
  "command": "docker",
  "args": [
    "run",
    "--rm",
    "-i",
    "--env",
    "CORTEX_API_TOKEN=YOUR_API_TOKEN_HERE",
    "ghcr.io/cortexapps/cortex-mcp:latest"
  ]
}'

If successful, you should see: “Added stdio MCP server cortex to local config”

Cursor

{
  "mcpServers": {
    "cortex": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "--env",
        "CORTEX_API_TOKEN=YOUR_API_TOKEN_HERE",
        "ghcr.io/cortexapps/cortex-mcp:latest"
      ]
    }
  }
}

VSCode

VS Code MCP Servers Documentation

Sample .vscode/mcp.json

{
  "inputs": [
    {
      "type": "promptString",
      "id": "cortex-key",
      "description": "Cortex API Key",
      "password": true
    }
  ],
  "servers": {
    "Cortex": {
      "type": "stdio",
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",