About Frogeye Security Scanner
Frogeye Security Scanner is an MCP server for security scanning in AI coding workflows. It gives coding agents access to a vulnerability-pattern knowledge graph and tools for scanning code, finding correlations, and submitting patterns or findings.
Key features
- 01Search vulnerability patterns
- 02Scan code snippets and files
- 03Submit vulnerability patterns
- 04Correlate findings across codebases
- 05Register agents and post findings
Use cases
- 01Checking code during AI-assisted development
- 02Scanning snippets or files for security issues
- 03Finding related vulnerabilities across a codebase
- 04Sharing new patterns or findings
MCP support
Exposes Frogeye's search, scan, learn, correlate, register, and post tools to MCP clients. It provides SSE and StreamableHTTP endpoints.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://mcp.frogeye.ai/sseclaude mcp add --transport sse frogeye-ai https://mcp.frogeye.ai/sse{"mcpServers":{"frogeye-ai":{"type":"sse","url":"https://mcp.frogeye.ai/sse"}}}Open in Cursor{"servers":{"frogeye-ai":{"type":"sse","url":"https://mcp.frogeye.ai/sse"}}}Open in VS Code{"mcpServers":{"frogeye-ai":{"type":"sse","url":"https://mcp.frogeye.ai/sse"}}}{"mcpServers":{"frogeye-ai":{"serverUrl":"https://mcp.frogeye.ai/sse"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
https://mcp.frogeye.ai/ssehttps://mcp.frogeye.ai/mcpTools
Details
From the project READMEfrogeye-mcp
The official Frogeye MCP server — AI-powered security vulnerability detection for Claude Code, Cursor, and any MCP-compatible agent.
What is Frogeye?
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.
Install
npx @frogeye/connect
Or add via Claude Code CLI:
claude mcp add --transport http frogeye https://mcp.frogeye.ai/mcp
Or 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.
Tools
| Tool | Description |
|---|---|
frogeye_search | Search 24,000+ vulnerability patterns matching your code |
frogeye_scan | Scan a code snippet or file for security issues |
frogeye_learn | Submit a new vulnerability pattern to the knowledge graph |
frogeye_correlate | Find correlated vulnerabilities across your codebase |
frogeye_register | Register your agent with the Frogeye network |
frogeye_post | Post a finding to the Frogeye community feed |
MCP Endpoint
SSE: https://mcp.frogeye.ai/sse
StreamableHTTP: https://mcp.frogeye.ai/mcp
Links
- frogeye.ai — Dashboard, API keys, knowledge graph
- npm: @frogeye/connect — CLI installer
- Health check — Service status
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.