Search

Open-source MCP/A2A security gateway — policy enforcement, taint tracking, sandboxed execution, deterministic envelopes, and Sigstore audit for every AI agent tool call. OWASP ASI 2026 compliant.

AI security MCP server and enforcement gate for Claude Code, Cursor, GitHub Copilot, Codex, Replit, and any MCP-compatible editor. Applies OWASP, MITRE ATT&CK, NIST, Zero Trust, PCI DSS, SOC 2, and ISO 27001.

Enterprise-grade LLM security guardrail library — 100+ Active Guards, LLM Traffic Monitor, 509 tests, zero core dependencies. Protects against prompt injection, data leakage, PII exposure, tool poisoning, goal hijacking, and supply chain attacks.

[glama](https://glama.ai/mcp/servers/@duriantaco/mcp-skylos) 🐍 🏠 🍎 🪟 🐧 - Dead code detection, security scanning, and code quality analysis for Python, TypeScript, and Go. 98% recall with fewer false positives than Vulture. Includes AI-powered remediation.

Privacy-first security scanner for MCP server configurations

Security framework for AI-generated code. Prompts, checklists, and tools for Cursor, Claude, and Copilot.

Security scanner for AI agents and MCP servers. OWASP Agentic Top 10 mapping, SARIF output, CI/CD ready.

MCP security proxy — protect any MCP server with customizable policies, path/command constraints, rate limiting, and audit logging. Zero code changes required.

AI-aware security scanner for source code, CI/CD pipelines and containers. Detects prompt injection, RAG/agent/MCP risks, secrets, and OWASP LLM Top 10 issues.

Security scanner for AI agent skills & MCP servers. 173 detection rules. 13 categories. 5 registries monitored daily. OpenClaw detection included. No API keys, no cloud, no LLM. One binary. Detection engine behind Oktsec.

OpenClaw (personal AI assistant) host adapter for agent-harness-generator (MCP via ~/.openclaw/openclaw.json + workspace skills)

Transparent MCP proxy with OpenTelemetry tracing. Wrap any MCP server, persist traces to SQLite · Postgres · MySQL. No code changes needed.

Security scanner for MCP servers with vulnerability detection and prompt injection analysis.

Zero-code LLM security & observability proxy. Real-time prompt injection detection, PII scanning, and cost control for OpenAI-compatible APIs. Built in Rust.

ESLint plugin for Model Context Protocol (MCP) SDK security — catches tools registered without an input schema, so handlers never run on unvalidated client-supplied arguments.

MCPS -- MCP Secure. Cryptographic identity, message signing, and trust verification for the Model Context Protocol.

Agent supply chain security — scan packages, code, images, PDFs, and MCP payloads for adversarial attacks

AI agent memory security — detect, quarantine, and block memory-poisoning attacks (OWASP ASI06) before they reach an LLM agent

Harden your AI coding agent in 60 seconds. Security hooks, audit logging, and posture scoring for Claude Code, Cursor, Windsurf, and more.

SupraWall security gateway for AI agents. Provides deterministic guardrails for MCP agents.