Search

Audit what your AI coding assistant loads before you type: token cost, dead weight, and MCP security risk — across Claude Code, Codex, Cursor and Copilot.

Agent-embedded security monitor. Instruments the four agent boundaries (model-client, framework tool-dispatch, MCP, effect) and reports findings to a control plane.

ddot -- The Security Protocol for Agentic AI. Ed25519 signing, Wasm sandboxing, 5-layer prompt firewall, and tamper-evident audit chains for MCP servers.

MCP Server for TDCC (Taiwan Depository & Clearing Corporation) — AI-callable tools for Taiwan securities custody open data via Model Context Protocol

TestForge MCP Server — AI-powered testing in your IDE. Analyzes code for security, unit tests, load, accessibility, vision alignment, scope coverage, and stack quality.

Security scanner and runtime proxy for Model Context Protocol (MCP) servers — catches tool poisoning, prompt injection, and silent behavior drift before they reach your AI agent.

Self-contained agentic development harness for Claude Code — one command runs the full feature pipeline (plan → execute → double review) with security gates baked in.

Adaptive context and runtime optimization for coding agents—reducing token waste, externalizing tool output, preserving exact session history, and enforcing secure tool routing.

A security minded, Blender MCP server, enabling mechanistic vibe coding edits for Blender to enable VR Avatar and World Creation and Editing + 3d printing modeling

Sayver MCP server — run security, legal/GDPR, and code scans from any MCP-compatible AI client (Claude Desktop, Cursor, Continue, Windsurf, Codex CLI).

Local, offline security scan for AI agent setups: audit the skills, MCP servers, hooks and permission grants an agent auto-loads, and vet one before installing it.

QAEverest MCP server: an AI QA copilot for any MCP client. Generate test cases grounded in your codebase, run automation suites, and run security and performance checks.

Universal AI Agent Kernel & Terminal Control Center. Rust-based hardened kernel with Vigils security, real-time observability, and tamper-evident audit ledger.

MCP server for the OpSpawn x402 Bazaar — screenshot capture, AI analysis, PDF/HTML generation, code security scanning, and dependency auditing via x402 micropayments

Model Context Protocol (MCP) server that enables Claude to perform comprehensive security audits on Solidity smart contracts using Slither, Aderyn, and built-in pattern detection

A sovereign, local-first MCP server for Technical SEO DNS record auditing, SOA health checks, SSL/TLS inspection, and HTTP security header analysis.

Self-running, provider-agnostic security audit — deterministic Tier-0 core plus optional pluggable LLM enrichment (Claude/OpenAI/Ollama). Not tied to Claude.

OSIM （Open Security Information Model）是 面向 AI 的开源安全数据标准化 项目，通过定义规范统一的安全数据 schema 语义层，破解行业数据碎片化难题，使安全团队、工具和 AI 系统能够在不同的数据源之间进行一致性推理和分析。致力于实现跨厂商、跨产品的安全数据无缝对接，为安全智能化升级与建立协同防御的核心数据打基础！

A Model Context Protocol (MCP) server for Blackduck and Server APIs, built with Node.js. Provides comprehensive tools for listing BOM, Operational risks and security issues

AI-powered supply chain security. Blocks malicious packages at install and import time. Works with Claude Code, Cursor, Devin, and every AI coding agent.