Cortex Threat Intelligence MCP server for AI agents

This MCP Server for Cortex serves as a bridge that exposes Cortex's powerful analysis capabilities to Model Context Protocol (MCP) clients, such as Claude. It enables language models to leverage Cortex analyzers for various threat intelligence tasks including IP analysis, URL scanning, and more.

Prerequisites

Rust Toolchain: Install Rust from rustup.rs
Cortex Instance: You need a running Cortex instance with network access
API Key: A Cortex API key with permissions to list analyzers and run jobs
Configured Analyzers: The specific analyzers you plan to use must be enabled and properly configured in your Cortex instance

Installation

Using Pre-compiled Binaries (Recommended)

Navigate to the GitHub Releases page
Download the appropriate binary for your operating system:
- mcp-server-cortex-linux-amd64
- mcp-server-cortex-macos-amd64
- mcp-server-cortex-windows-amd64.exe
Prepare the binary:
- Move it to a suitable location (e.g., /usr/local/bin on Linux/macOS)
- For Linux/macOS, make it executable:
```
chmod +x /path/to/your/mcp-server-cortex
```
- Ensure the directory is in your system's PATH if needed

Building From Source

Clone the repository:

git clone https://github.com/gbrigandi/mcp-server-cortex.git
cd mcp-server-cortex

Build the project:
- For a debug build:
```
cargo build
```
- For a release build (recommended):
```
cargo build --release
```

Configuration

Configure the server using these environment variables:

CORTEX_ENDPOINT: The full URL to your Cortex API (e.g., http://localhost:9000/api)
CORTEX_API_KEY: Your API key for authenticating with Cortex
RUST_LOG (Optional): Controls logging level (e.g., info or mcp_server_cortex=debug,cortex_client=info)

Cortex Analyzer Configuration

The following analyzers must be enabled and configured in your Cortex instance:

AbuseIPDB_1_0: Used by the analyze_ip_with_abuseipdb tool (requires AbuseIPDB API key)
Abuse_Finder_3_0: Used by the analyze_with_abusefinder tool
VirusTotal_Scan_3_1: Used by the scan_url_with_virustotal tool (requires VirusTotal API key)

Ensure you enable these analyzers in your Cortex instance's "Organization" → "Analyzers" section and configure them with the necessary API keys.

Claude Desktop Configuration

For MCP clients like Claude Desktop:

Configure your client to point to the MCP server executable
Example claude_desktop_config.json:

{
  "mcpServers": {
    "cortex": {
      "command": "/opt/mcp-servers/mcp-server-cortex",
      "args": [],
      "env": {
        "CORTEX_ENDPOINT": "http://your-cortex-instance:9000/api",
        "CORTEX_API_KEY": "your_cortex_api_key_here"
      }
    }
  }
}

Available Tools

analyze_ip_with_abuseipdb

Analyzes an IP address using AbuseIPDB via Cortex.

Parameters:

ip (string, required): The IP address to analyze
analyzer_name (string, optional): The specific analyzer instance. Defaults to AbuseIPDB_1_0

analyze_with_abusefinder

Analyzes various types of data using AbuseFinder via Cortex.

Parameters:

data (string, required): The data to analyze (e.g., "1.1.1.1", "example.com")
data_type (string, required): The type of data. Must be one of: ip, domain, fqdn, url, mail
analyzer_name (string, optional): The specific analyzer instance. Defaults to Abuse_Finder_3_0

scan_url_with_virustotal

Scans a URL using VirusTotal via Cortex.

Parameters:

url (string, required): The URL to scan
analyzer_name (string, optional): The specific analyzer instance. Defaults to VirusTotal_Scan_3_1

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "cortex" '{"command":"/opt/mcp-servers/mcp-server-cortex","args":[],"env":{"CORTEX_ENDPOINT":"http://your-cortex-instance:9000/api","CORTEX_API_KEY":"your_cortex_api_key_here"}}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cortex": {
            "command": "/opt/mcp-servers/mcp-server-cortex",
            "args": [],
            "env": {
                "CORTEX_ENDPOINT": "http://your-cortex-instance:9000/api",
                "CORTEX_API_KEY": "your_cortex_api_key_here"
            }
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "mcpServers": {
        "cortex": {
            "command": "/opt/mcp-servers/mcp-server-cortex",
            "args": [],
            "env": {
                "CORTEX_ENDPOINT": "http://your-cortex-instance:9000/api",
                "CORTEX_API_KEY": "your_cortex_api_key_here"
            }
        }
    }
}

3. Restart Claude Desktop for the changes to take effect