Back to Integrations

LiteSOC MCP Server for AI Editors

Give Cursor, Claude Desktop, and GitHub Copilot live access to your LiteSOC alerts, events, and forensic intelligence via the MCP Server.

Last updated: 2026-04-11

LiteSOC MCP Server for AI Editors

The LiteSOC MCP Server (@litesoc/mcp-server) is an official Model Context Protocol server that gives AI editors direct, live access to your LiteSOC security data — alerts, forensic intelligence, event logs, and incident resolution.

What You Can Do

With the MCP Server connected, you can ask your AI editor questions like:

  • "Show me all open critical alerts"
  • "Analyze alert alt_abc123 — is this a real attack?"
  • "Get the last 20 failed login events"
  • "Resolve alert alt_abc123 as a false positive"

The AI gets live data from your LiteSOC project and can reason about threats, suggest remediation, and resolve incidents — all from your editor.

Prerequisites

  • Node.js 18+
  • A LiteSOC API key (lsk_live_...) from Settings → API Keys
  • Pro or Enterprise plan for alert access and full forensic intelligence

Setup in Cursor

Go to Settings → MCP → Add Server and add:

{
  "mcpServers": {
    "litesoc": {
      "command": "npx",
      "args": ["-y", "@litesoc/mcp-server"],
      "env": {
        "LITESOC_API_KEY": "lsk_live_your_api_key_here"
      }
    }
  }
}

Setup in Claude Desktop

Edit the config file:

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%\Claude\claude_desktop_config.json
{
  "mcpServers": {
    "litesoc": {
      "command": "npx",
      "args": ["-y", "@litesoc/mcp-server"],
      "env": {
        "LITESOC_API_KEY": "lsk_live_your_api_key_here"
      }
    }
  }
}

Restart Claude Desktop after saving.

Available Tools

The MCP Server exposes four tools:

ToolDescriptionParameters
list_alertsFetch open security alertsstatus, severity, alert_type, limit (1–50)
analyze_alertFull forensic detail for a single alert — VPN/Tor detection, geolocation, ISP, threat scorealert_id
get_recent_eventsFetch latest raw security event logslimit (1–50), event_name, actor_id, severity
resolve_incidentMark an alert as resolved with SOC 2 audit trailalert_id, resolution_type, notes

Resolution Types

When resolving an incident, use one of:

  • blocked_ip — Source IP has been blocked
  • reset_password — User password was reset
  • contacted_user — User was contacted to verify
  • false_positive — Not a real threat
  • other — Custom resolution

Plan Requirements

FeatureFreeProEnterprise
get_recent_events✅ (network intel redacted)
list_alerts
analyze_alert
resolve_incident

Every response includes a footer showing your current plan, retention window, and data cutoff date.

Security

  • All queries are scoped to your organization and project (tenant isolation enforced server-side)
  • The API key is read from the environment at runtime — never persisted or logged by the server
  • Uses stdio transport — no network ports are opened on your machine

Troubleshooting

"Check your LITESOC_API_KEY"

  • Verify the key starts with lsk_live_
  • Ensure the key has not been revoked in your dashboard
  • Check the env block in your MCP config

"Upgrade to Pro"

Alert-related tools (list_alerts, analyze_alert, resolve_incident) require a Pro or Enterprise plan.

"Outside retention window"

The alert or event ID may be older than your plan's retention period. Check the X-LiteSOC-Cutoff date in the response footer.


Need help? Check our API documentation or contact support.

Related Articles

Was this article helpful? Need more assistance?