sinewaveai/agent-security-scanner-mcp

Security scanner MCP server for AI coding agents. Prompt injection firewall, package hallucination detection (4.3M+ packages), 1000+ vulnerability rules with AST & taint analysis, auto-fix.

49
/ 100
Emerging

This tool helps developers and security engineers working with AI coding agents to ensure the code produced is secure and trustworthy. It takes code snippets, agent prompts, or entire projects as input and identifies potential vulnerabilities like prompt injection, hallucinated software packages, and common code exploits. The output is a security assessment, including auto-fixes, to protect against malicious code and data breaches.

Available on npm.

Use this if you are developing with AI coding agents and need to automatically scan generated code for security vulnerabilities, detect fake dependencies, and prevent prompt injection attacks.

Not ideal if you are solely working with traditional, human-written codebases and don't require specific protections against AI agent-generated threats or compliance frameworks like SOC2 and GDPR.

AI-agent-security application-security software-supply-chain code-auditing compliance-auditing
Maintenance 10 / 25
Adoption 9 / 25
Maturity 20 / 25
Community 10 / 25

How are scores calculated?

Stars

79

Forks

6

Language

JavaScript

License

MIT

Last pushed

Mar 11, 2026

Commits (30d)

0

Dependencies

4

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/mcp/sinewaveai/agent-security-scanner-mcp"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.