Loading...

This MCP server bridges LLMs to a Cortex instance for threat intelligence, enabling analysis of observables like IPs and URLs via configured analyzers.
Boost this tool
Subscribe to listing upgrades or segmented pushes.
This MCP server bridges LLMs to a Cortex instance for threat intelligence, enabling analysis of observables like IPs and URLs via configured analyzers.
This server is relatively safe for read-only operations, but the security posture depends heavily on the configuration of the Cortex instance and the protection of the API key. It is risky if the Cortex instance is not properly secured or if the API key is exposed.
Performance depends on the Cortex instance and the external services used by the analyzers. Network latency can also impact performance.
Cost depends on the usage of external services like VirusTotal and AbuseIPDB, which may have API usage limits or subscription fees.
{
"mcpServers": {
// ... other server configurations ...
"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",
}
}
// ... other server configurations ...
}
}analyze_ip_with_abuseipdbAnalyzes an IP address using AbuseIPDB via Cortex and returns the job report.
Read-only operation that queries AbuseIPDB for IP reputation.
analyze_with_abusefinderAnalyzes data (IP, domain, URL, etc.) using AbuseFinder via Cortex and returns the job report.
Read-only operation that queries AbuseFinder for threat intelligence.
scan_url_with_virustotalScans a URL using VirusTotal via Cortex and returns the job report.
Read-only operation that submits a URL to VirusTotal for scanning.
analyze_url_with_urlscan_ioAnalyzes a URL using Urlscan.io via Cortex and returns the job report.
Read-only operation that submits a URL to Urlscan.io for analysis.
API Key
This server is relatively safe for read-only operations, but the security posture depends heavily on the configuration of the Cortex instance and the protection of the API key. It is risky if the Cortex instance is not properly secured or if the API key is exposed.
Autonomy is limited by the read-only nature of the tools. The LLM can request analysis, but cannot modify the Cortex instance or take destructive actions.
Production Tip
Monitor Cortex performance and API usage to ensure the server can handle the load.
The tool call will likely fail or return an error from Cortex. Ensure all analyzers are enabled and configured with the necessary API keys.
Store the API key securely and avoid committing it to version control. Use environment variables to pass the key to the server.
Yes, any MCP-compatible client should be able to use this server. However, compatibility may vary depending on the client's implementation.
You can analyze IPs, URLs, domains, and other observables supported by the configured Cortex analyzers.
You can specify the analyzer name as a parameter in the tool call. If not specified, the server will use the default analyzer name.
Check the server logs and the Cortex logs for error messages. Ensure the analyzer is configured correctly and that the Cortex instance is running.
The server itself likely supports concurrent requests, but the performance will depend on the Cortex instance and the external services used by the analyzers.