Security Review

MCP security scanner: detect tool poisoning, prompt injection & rug-pulls - 10 OWASP heuristics.

The dependency bloodhound for AI coding agents. Zero API keys, zero config.

The security layer for AI agents — platform-agnostic threat detection with 300+ rules, runtime blocking, and remediation guidance. Continuous protection.

align CLI — an architecture-conformance verification oracle for LLM coding agents, with a built-in MCP server.

Security scanner for AI agent tools. Local static scan of MCP IDE configs (41 rules, toxic flow heuristics, AAuth visibility, auto-fix, tool pinning). Optional proxy + in-browser dashboard: traffic, findings, AAuth Explorer, YARA, Playground. Smart Scan o

Safety-ranked open-source component discovery for agents across six package ecosystems.

Static preflight safety gate for MCP servers — scan configs before you run them. Never executes.

Model Context Protocol server for OAuthLint. Lets AI coding tools scan their own generated OAuth/OIDC/JWT/session/CORS code for the anti-patterns OAuthLint catches, in-loop.

Structured graph capabilities for AI agents consuming Ontoly.

kipmox Guardrails — deterministic Salesforce code review, independent fix verification, and change-impact (blast-radius) analysis, as an MCP server for AI coding agents (Claude Code, Cursor, …).

The deterministic trust layer for autonomous AI coding agents. Compiler-grounded verification of what an agent actually did vs. what it claimed, blast radius mapping, and persistent contract memory.

Pre-deploy ship gate AI agents call before shipping. Also audits the agent's own MCP config.

Structural code intelligence for DeepSeek Harness — gives the agent codegraph and codegraph_index tools to find where a symbol is declared, what calls it, what a change reaches, and how one symbol reaches another, from a tree-sitter index it builds itself

AI-DOS: Code Intelligence Platform — knowledge graphs, security scanning, and closed-loop AI development via MCP tools, sub-agent prompts, security rules, and CLI workflows.

Multi-engine AI agent security scanner — one scan, four engines, one report

npm dependency fitness: deprecated/yanked/superseded + verified safe migration target.

A simple Node.js module that fetches and parses the latest Common Weakness Enumeration (CWE) list

AI Agent 开发质量守护工具 — 30+规则检测代码缺陷/安全漏洞/性能反模式，多引擎AI根因分析，零外部依赖

Recent CVE + GHSA cache for AI agents auditing dependencies (npm/PyPI/Cargo/Maven/Go).

Structural code intelligence for DeepSeek Harness — gives the agent codegraph and codegraph_index tools to find where a symbol is declared, what calls it, what a change reaches, and how one symbol reaches another, from a tree-sitter index it builds itself