Frogeye Security Scanner

Name: Frogeye Security Scanner
Author: frogeye-ai

@frogeye-ai

About Frogeye Security Scanner

Zero-config security scanner for AI-generated apps. 25K+ vulnerability patterns. Works with Claude Code, Cursor and any MCP-compatible agent.

#security #mcp #vulnerability #claude #vibe-coding

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "frogeye": {
      "command": "npx",
      "args": [
        "-y",
        "@frogeye/connect"
      ],
      "env": {
        "FROGEYE_API_KEY": "<YOUR_KEY>"
      }
    }
  }
}

Tools

semantic search across 25K+ vulnerability patterns

scan code snippets for known vulnerabilities

contribute patterns back to the knowledge graph

find related vulnerability patterns across your codebase

Overview

What is Frogeye Security Scanner?

Frogeye Security Scanner is a security knowledge graph for AI-generated apps. It catches vulnerabilities that AI coding agents introduce, such as SQL injection, broken auth, exposed credentials, and XSS. It is designed for developers using MCP-compatible agents like Claude Code and Cursor.

How to use Frogeye Security Scanner?

Install via npx @frogeye/connect. Your MCP-compatible agent automatically queries Frogeye during code review. Get your API key at frogeye.ai (free tier includes 25 queries/day, no credit card required).

Key features of Frogeye Security Scanner?

Semantic search across 25K+ vulnerability patterns
Scan code snippets for known vulnerabilities
Contribute patterns back to

Comments

Basic information

More Developer Tools MCP servers

Reelier

Maxime Houle

Agents make claims. Reelier writes receipts — record an agent's tool-call workflow once, replay it deterministically at 0 tokens, and diff runs to catch drift.

Skilder.ai

skilder.ai

Run skills and MCP tools like production software: versioned, composed into roles, distributed to every agent from one governed library.

Apiosk

obcraft

AI-native payments for tools and APIs. Discover, pay for, execute, and publish monetized APIs directly from your agent, settled per call in USDC over x402, through the Model Context Protocol. payments · finance · x402 ·

AptiBuild AI — Career Intelligence

ParklandBuilds

AptiBuild AI — Career Intelligence MCP Server Structured career decision scaffolding for AI agents. Provides personality-conditioned business idea generation, official BLS OEWS wage data, FRED labor market signals, and

CircleCI MCP Server

CircleCI

Manage CI/CD pipelines, debug failed builds, and optimize test suites directly from your AI agents - no terminal required. The CircleCI MCP Server is a remote server hosted by CircleCI that connects AI tools and agents