Find vulnerabilities and insecure patterns in code.
Scan a project for leaked secrets, risky MCP configs, and unsafe automation before handing it to an AI coding agent (Claude Code, Cursor, Codex). Zero dependencies, runs locally.
Know where every prop comes from — MCP server for Claude Code, Cursor & Copilot, a CI check with GitHub annotations, one-command prop-drilling fixes, and an interactive React state graph.
Production-ready MCP server for intelligent JavaScript package management. Works with Claude, Windsurf, Cursor, VS Code, and any MCP-compatible AI editor.
Durable, build-scoped reverse-engineering evidence memory and query tools for AI agents.
Scans code changes for leaked secrets and insecure config, with actionable fixes for AI agents.
Proof-carrying debugger. Executes your code to find a real failing input, verifies the failure three ways before reporting it, generates candidate repairs, and rejects patches that only fit the example that caught them. CLI, MCP server, or programmatic AP
Goosy MCP server — exposes Goosy's security-scan engine to AI coding agents over the Model Context Protocol.
Andesyte local security CLI and MCP server: check code and dependencies without uploading source.
Lightweight dependency vulnerability audit tool with CLI and MCP Server support
Static analysis engine for JavaScript and TypeScript dependency graphs, health scoring, dependency-chain explanations, unused exports, unresolved imports, impact analysis, architecture rules, and AI-agent tooling.
Shodan MCP Server – network reconnaissance, DNS operations, and vulnerability intelligence
List the tools your AI agent can call, ranked by how dangerous they are, and which are unguarded.
RepoSkein gives your AI coding agent a map of your codebase — so it navigates structure instead of grepping and guessing.
CTRL_ — security audit MCP server for AI-generated Next.js, Vite and Express apps. Finds exposed keys, unsafe queries and open row-level security, then walks your coding agent through fixing them. Extra depth on Supabase.
Chanakya MCP: Local Model Context Protocol server delivering deep structural AST intelligence and 80-93% token reduction for AI coding agents.
MCP server for depsight — query CVE, license, dependency and CI data from Claude / other agents
Cited structure of Java/Spring/Angular codebases: dependencies, tables, endpoints, hotspots.
MCP server for real-time dependency security — checks packages against CVE databases before your AI coding agent installs them. Works with Cursor, Claude Code, Windsurf, and any MCP-compatible IDE.
Core engines for AI agent trust scoring, OWASP analysis, permission extraction, and attack detection
Security scanner for MCP servers. Find vulnerabilities before your AI agent does.