75 packages found
An MCP server to create secure code sandbox environment for executing code within Docker containers. This MCP server pro
MCE (MCP Code Execution) is a production-grade MCP server that transforms Swagger/OpenAPI specs into LLM-native Python f
A coding agent CLI hook that acts as a safety net, catching destructive git and filesystem commands before they execute.
A secure* runtime for autonomous AI agents. Policy from plain-English constitutions. (*https://ironcurtain.dev)
Give each AI agent its own isolated machine with root, Docker, and systemd. Active defense detects and stops threats aut
Local-first security scanner, MCP protocol inspector, dynamic fuzzer, Docker sandbox, and report generator for Model Con
Local-first personal agentic OS and everything app for coding, knowledge work, web design, automations, and artifacts.
Reverse Engineering / Authorized Penetration Testing / Security Research Skill Router Pack AI-powered routing + On-deman
AI agent security scanner. Detect vulnerabilities in agent configurations, MCP servers, and tool permissions. Available
Security infrastructure your AI can't be — deterministic, daily CVE intel past your model's training cutoff, whole-repo-
@anthropics✓ OfficialSkills for threat modeling, scanning, triage, patching, plus an autonomous scanning harness you can /customize
Browser-automation agent for Chrome — natural-language tasks executed through native tool calling, scoped Skills, CDP ke
Secure MCP server for safe AI-powered terminal access with risk analysis, sandboxing, logging, filesystem protection, an
A secure, stable Rust alternative to openclaw/moltbot/clawdbot
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development f
MCP server for VirusTotal API — analyze URLs, files, IPs, and domains with comprehensive security reports, relationship
Complete Claude skills toolkit for professional malware analysis. 5 specialized skills covering triage, dynamic analysis
Security, cost, and health governance proxy for MCP infrastructure — YAML policy engine, OAuth 2.1/OIDC, web dashboard,
Run Claude in self-improving loops to optimize measurable goals.
Policy-as-code for MCP agents: deny risky tool calls before they run, prove what ran with verifiable evidence, and enfor
Trust nothing. Ship safely. — Skeptical-reading and prompt-injection defense skill for AI agents. Provenance tagging, re
A self-hosted sandbox for red teams to test payloads against modern detection before deployment. MCP integration lets an
The approval and accountability layer for agentic AI. Identity → Policy → Approval → Trace. Try: npx sidclaw-mcp-guard d
[DEPRECATED] Moved to microsoft/agent-governance-toolkit
Open-source runtime security and governance for AI agents, MCP tools, robotics, industrial automation, and physical AI.
rUvOS — the agentic operating system. A single static Rust binary that runs as an MCP server, giving Claude Code persist
AI agent firewall that intercepts tool calls (file, shell, network) and enforces deterministic policies at sub-microseco
GoClaw - GoClaw is OpenClaw rebuilt in Go — with multi-tenant isolation, 5-layer security, and native concurrency. Deplo
A curated, DevOps-focused list of Model Context Protocol (MCP) servers—covering source control, IaC, Kubernetes, CI/CD,
🔬 Mobile runtime detection workbench for AI (iOS and Android)
Fully autonomous AI Agents system capable of performing complex penetration testing tasks
Implementation of the CodeAct agentic framework with Docker containers for security, MCP servers for tool integrations,
AI supply-chain security scanner and self-hosted control plane for agents, MCP, SBOM/SARIF, graph findings, runtime enfo
awsome kali MCPServers is a set of MCP servers tailored for Kali Linux
The Complete AI Development Toolkit for Claude Code — 103 skills, 36 agents, 172 hooks. Production-ready patterns for fu
Official companion repository for our survey "A Survey of the OpenClaw Ecosystem: From Platform Extensibility to Constra
Vlad's Playbook — the operator's field manual where every artifact is live, clickable, and forwardable. 39 chapters · 25
Open source local-first PR scanner that finds dead code, security bugs, secrets, quality regressions, and AI-code mistak
Multi-driver TUI database client with a built-in MCP server. Six databases (postgres, mysql, sqlite, duckdb, clickhouse,
Local-first Model Context Protocol (MCP) memory layer for Codex CLI/Desktop, Claude Code, Gemini CLI, Qwen/DeepSeek/Olla
@microsoft✓ OfficialWassette: A security-oriented runtime that runs WebAssembly Components via MCP
Open-source toolkit for the QVeris capability routing network: CLI, MCP server, Python SDK, skills, and REST API docs fo
754 structured cybersecurity skills for AI agents · Mapped to 5 frameworks: MITRE ATT&CK, NIST CSF 2.0, MITRE ATLAS, D3F
The trust economy for autonomous AI agents. Credit scores for machines. Agents earn Trust Capital through verified behav
The first quantum-inspired keyring built specifically for AI coding agents. Secure secrets with superposition, entanglem
AI Agent Security Middleware — 8-layer defense, DLP data flow, prompt injection detection, zero dependencies. SDK + MCP
GUARDRAIL - MCP Security - Gateway for Unified Access, Resource Delegation, and Risk-Attenuating Information Limits
Agent Hub is an AI orchestration platform that transforms how developers and DevOps engineers interact with their toolch
A generic mcp server fuzzer