MCP servers for security scanning, vulnerability testing, secrets management and QA automation. Each entry is scanned with the deterministic Capability-Flow Trust Model — grades are computed, never self-reported.
MCP server for the Codex Security Cloud service.
A safety layer for AI coding agents before they touch your repo.
Secure shell execution for AI agents — MCP server + CLI
AI-powered security audit MCP server with real-time vulnerability data
MCP-SecLint: Static analysis tool for detecting vulnerabilities in MCP server implementations
SOVR MCP Proxy — intercepts MCP tool calls and evaluates them against the unified Policy Engine
Adaptive threat intelligence for AI agent security — semantic memory, multi-turn escalation, output scanning, rate limiting, and prompt hardening.
Multi-agent framework with persistent expert sessions and context isolation — MCP server for Claude Code
MCP server for EU AI Act compliance scanning with GDPR and bias detection - scan, analyze, remediate, and protect AI agent code
MCP server that vets LLM-emitted shell commands BEFORE execution. Detects rm -rf in chains, current-dir wipes (the chiefofautism 'rm -rf your repo' pattern), find-exec-rm, package-glob removal (including --purge form and trailing globs like python3-*), dd/mkfs/wipefs, chmod 777, curl|bash + wget|sh + base64-decode|bash obfuscation, chained shutdown, git destructive ops. 30 rules / 8 families. Sub-second, local, no API key. Defensive complement to MCPShell/mcp-shell/mcp-bash.
MCP server for Beaker lab automation — system provisioning, job management, distro discovery, and failure diagnosis
Contextual blast-radius scoring for shell commands an AI agent is about to run
MCP server exposing 29 AI coding skills — autonomous commits, loops, reviews, incident response, and more
Consult a council of AI CLIs (Gemini, GPT, Claude, Mistral, Qwen, Copilot, OpenCode…) from inside any MCP client — free and ban-safe.
Code similarity firewall - blocks dangerous code patterns before they reach execution tools
Policy-as-code enforcement for AI agents with MCP, CEL, Git hooks, SARIF, and static-analysis guardrails.
Hard state for AI agents: typed, governed, durable state with deterministic queries, governed writes, and receipts.
Model Context Protocol tool for Fleet DM integration
AI agent tools for Open Security Controls Assessment Language (OSCAL).
Vet AI-agent content (MCP servers, skills, plugins) for malicious code before you install it.
SpecFlow MCP Server and CLI — spec-driven AI code generation
Deception middleware for AI agents - detecting data theft and indirect prompt injection in MCP servers
Hospital Vulnerability Scanner MCP Server - Security scanning for healthcare systems
Vibe reversing with IDA Pro