isMalicious threat intelligence for AI agents

Overview

isMalicious threat intelligence for AI agents is an MCP server that brings security intelligence directly into your AI workflows. It provides indicator reputation verdicts, CVE lookups with CVSS and EPSS scores, KEV data, and prompt-injection scanning—all tools your AI assistant can invoke to strengthen security decisions and protect against threats.

The server runs locally on your machine via the npm package @ismalicious/mcp-server, which communicates over stdio. You'll need an API key to authenticate. Version v0.3.0 is the latest release.

isMalicious threat intelligence for AI agents is listed in the AI & Agents category and works with MCP clients including Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, Zed, and others. If you maintain this server, claim this listing to verify ownership, earn a Verified badge, and keep information up to date.

Installation

// claude_desktop_config.json
{
  "mcpServers": {
    "ismalicious_threat_intelligence_for_ai_agents": {
      "command": "npx",
      "args": [
        "-y",
        "@ismalicious/mcp-server"
      ]
    }
  }
}