MCP servers and skills: search, filter by where they run, and compare.
Enterprise reference architecture for governed Agentic SOC, MSSP, MDR, Cloud IR, and private/local LLM-assisted DFIR operations.
PythonApache-2.0★ 4Few starsNo key
An end-to-end agentic pipeline that accepts code repositories, log files, screenshots, and architecture diagrams, runs specialized MCP (Model Context Protocol) security tools, correlates findings acro
SkillMIT★ 1Few starsNo key
Agentic security CLI that finds reachable vulnerabilities, writes the fix, and attacks its own patch in an isolated Nebius sandbox. A patch is certified only when the live exploit fails. Powered by NV
PythonMIT★ 1Few starsNo key
🔌 Exposes OWASP Top 10 for Agentic AI security over MCP — prompt injection detection, tool poisoning, excessive agency, data leakage assessment
PythonMITFew starsNo key
Hyperdope is a suite of autonomous agents that audit code, hunt 0days, and ship coordinated-disclosure advisories - the way a top-tier research team works, at machine speed.
Node.jsMIT★ 8No key
An open-source, AI-native Model Context Protocol (MCP) server bridging Large Language Models with core network diagnostic tools for automated observability, threat detection, and agentic security orch
MCPLink only★ 1Few stars
Progressive Recursive Agentic Vulnerability Assessment Lifecycle — self-hostable agentic AI framework applying continuous LLM reasoning across all 10 phases of enterprise VA with progressive context c
SkillMIT★ 5No key
Turn Claude, ChatGPT, and any LLM into a safe, bloat-free Autonomous Coding Agent with semantic navigation and worktree sandboxing.
Node.jsMIT★ 2Few starsNo key
Deterministic untrusted-text inspection with paid x402 HTTP and MCP tools on Base
Hosted by authorMITFew starsNo key
The "Metasploitable" of MCP — a deliberately vulnerable Model Context Protocol server for agentic-security training, mapped to the OWASP Top 10 for Agentic Applications.
MCPLink only★ 7
A framework for building and running your own living GenAI/LLM threat model. Ships with a curated reference catalog, an LLM-driven assessor, and an MCP server
PythonApache-2.0★ 1Few starsNo key
AgentGuard is the open-source security layer for Google ADK agents, blocking risky MCP actions, routing sensitive calls for approval, and delivering enterprise auditability.
SkillApache-2.0★ 1Few starsNo key
Local security layer for AI coding agents that blocks secret leaks, destructive commands, unsafe Git operations, and unauthorized network access.
MCPLink only★ 1Few stars
Local MCP proxy that governs what AI agents do on your machine. Policy enforcement, audit receipts, hash-chained provenance.
PythonApache-2.0Few starsNo key
Secure agentic GitHub remediations with MCP, OAuth-gated tool access, and GRC-grade evidence trails
SkillMITFew starsNo key
Guardian is a next-generation agentic security system built on the Model Context Protocol (MCP). Unlike static scripts, it uses LangGraph to autonomously reason through AWS infrastructure, identify cr
MCPLink only★ 1Few stars
Next Generation Agentic Proxy for AI Agents and MCP servers
GoApache-2.0★ 5.8kNo key
Open-source, self-hosted AI penetration testing framework: maps your attack surface into a graph, autonomously exploits it from a Kali sandbox with human approval gates, and opens PRs that fix what it
SkillMIT★ 3.3kNo key
A security scanner for your LLM agentic workflows
PythonApache-2.0★ 1.1kNo key
ADR secures enterprise AI agents through observability, security benchmarking, and threat detection. Deployed at Uber.
SkillApache-2.0★ 2.1kNo key
Put an end to code hallucinations! GitMCP is a free, open-source, remote MCP server for any GitHub project
SkillApache-2.0★ 8.5kNo key
Production-grade MCP server giving Claude 27 security intelligence tools across 21 APIs — CVE lookup, EPSS scoring, CISA KEV, MITRE ATT&CK, Shodan, VirusTotal, and more.
PythonApache-2.0★ 1.7kNo key
Who stands behind it
