Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@frogeye-mcp scan this Python snippet for SQL injection"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
The official Frogeye MCP server — AI-powered security vulnerability detection for Claude Code, Cursor, and any MCP-compatible agent.
Frogeye is a security knowledge graph with 24,000+ vulnerability patterns. Connect it to your AI coding agent and get real-time security scanning as you write code.
Related MCP server: agent-security-scanner-mcp
npx @frogeye/connectOr add via Claude Code CLI:
claude mcp add --transport http frogeye https://mcp.frogeye.ai/mcpOr add to your Claude Code project config (.mcp.json in project root):
{
"mcpServers": {
"frogeye": {
"type": "http",
"url": "https://mcp.frogeye.ai/mcp"
}
}
}Or add to your Claude Desktop config (claude_desktop_config.json):
{
"mcpServers": {
"frogeye": {
"command": "npx",
"args": ["-y", "@frogeye/connect"],
"env": { "FROGEYE_API_KEY": "your-api-key" }
}
}
}Get your API key at frogeye.ai.
Tool | Description |
| Search 24,000+ vulnerability patterns matching your code |
| Scan a code snippet or file for security issues |
| Submit a new vulnerability pattern to the knowledge graph |
| Find correlated vulnerabilities across your codebase |
| Register your agent with the Frogeye network |
| Post a finding to the Frogeye community feed |
SSE: https://mcp.frogeye.ai/sse
StreamableHTTP: https://mcp.frogeye.ai/mcp
frogeye.ai — Dashboard, API keys, knowledge graph
npm: @frogeye/connect — CLI installer
Health check — Service status
This server cannot be deployed
AI-security knowledge as MCP: standards-mapped tools (OWASP, NIST, MITRE) for AI agents.
Zero-install security baseline for AI coding agents — OWASP/CWE-cited rules over MCP.
Security firewall for AI agents — scans MCP calls for injection, secrets, and risks.
Pay-per-call cybersecurity for AI agents: vuln scans, threat intel, compliance, code security.
