- Conduid
- Marketplace
- #security-research
MCP servers tagged security-research
48 live MCP servers tagged "security-research", ranked by trust score. Tags come from package metadata and repository topics, so this list covers servers across every category that work with security-research.
Claude Code Analysis
We read all 512K lines of Claude Code's accidentally exposed source. 82 docs, 15 diagrams, every subsystem mapped — from the hidden YOLO safety classifier to multi-agent swarms.
Claude Code Analysis
We read all 512K lines of Claude Code's accidentally exposed source. 82 docs, 15 diagrams, every subsystem mapped — from the hidden YOLO safety classifier to multi-agent swarms.
OnionClaw
OnionClaw™ — OpenClaw skill for full Tor dark web access: search .onion sites, fetch hidden services, rotate identity, run OSINT pipeline, craw.
0
The multiplayer AI offensive security OS - open, self-improving, extensible. Find, verify, and fix vulnerabilities.
OnionClaw
OnionClaw™ — OpenClaw skill for full Tor dark web access: search .onion sites, fetch hidden services, rotate identity, run OSINT pipeline, craw.
0sec
[RESEARCH PREVIEW] The open & extensible cybersecurity harness - by the Swiss Applied AI Cybersecurity Research Lab.
Awesome AI Agent Attacks
A curated timeline of real AI agent security incidents, breaches, and vulnerabilities (2024-2026). Every entry sourced and dated.
Huntkit
Investigation toolkit for Claude Code: case management, OSINT, structured analytic techniques, chain-of-custody evidence capture, and bundled threat-intel MCP servers.
Ave
AVE - Agentic Vulnerability Enumeration. The open behavioral classification standard for agentic AI components.
Orca AI Incident Archive
An open database of real-world AI agent incidents.
Opencrow
Agentic AI orchestration framework for offensive security and CTF work, with Codex-ready skills, typed MCP servers, workflow CLIs, and OpenCROW Constellation for multi-agent coord…
OpenCROW
Agentic AI orchestration framework for offensive security and CTF work, with Codex-ready skills, typed MCP servers, workflow CLIs, and OpenCROW Constellation for multi-agent coord…
Aircrack MCP
MCP server that wraps aircrack-ng, enabling AI assistants to run and automate WiFi security assessments (scanning, handshake capture, cracking) for authorized penetration testing.
Sicry
Enable AI agents to access Tor and .onion sites with a simple Python layer supporting built-in search engines and OSINT tools.
Reconbridge
通用逆向分析 KernelSU 模块：手机侧只做原子能力，智能全在 PC 侧（Claude Code + MCP）。仅限授权安全研究与教育用途。
AI Pentest Playbook
🛡 The reference playbook for pentesting AI chatbots & LLM-powered apps in one place. Ready-to-use payloads covering the full OWASP LLM Top 10 plus frontier vectors (MCP · RAG · A2…
Aliensec MCP Server
AlienVault OTX Endpoint Security Scanning MCP Server with VirusTotal Integration
Flutter Apk Injector
Enterprise-grade Model Context Protocol (MCP) server for Android APK reverse engineering, Smali refactoring, native JNI tracing, and Flutter runtime injection powered by Hermes+ A…
Era Agent
ERA – Evolve & Reverse Engineer Anything: an AI-powered reverse-engineering agent built on REA, with a controlled, evidence-driven Improvement Lab. Reverse. Analyze. Evolve. Repea…
Flipper MCP
MCP server for driving a Flipper Zero over USB-CDC serial.
Remote Oauth Security
Seven evidence-bounded OAuth trust-boundary security advisories for geelen/mcp-remote, reviewed through 0.1.38.
AI Kubernetes Helm Chart Security
Evidence and data for the Sorami technical report on security defaults of 15 AI serving, vector database and MCP Helm charts on Kubernetes.
Sicry
Enable AI agents to access Tor and .onion sites with a simple Python layer supporting built-in search engines and OSINT tools.
Aether MCP
Uncensored AI tools for Claude Desktop, Cursor, Cline, Zed via Model Context Protocol
AI Infra Security
Vulnerability research on AI infrastructure: LLM gateways, MCP transports, and model-serving stacks. Root cause, reproduction, and detection.
Aircrack MCP
MCP server that wraps aircrack-ng, enabling AI assistants to run and automate WiFi security assessments (scanning, handshake capture, cracking) for authorized penetration testing.
CHIMERA
Chained Harm & Injection Measurement for Evaluating Risks in Agents — a red-team research framework that tests hosted models, agentic apps, RAG pipelines, MCP servers, AI coding a…
Urlhaus MCP Server
MCP server for accessing URLhaus malicious URL database from abuse.ch - provides threat intelligence for cybersecurity research
Pocmap
MCP-native CVE, PoC & exploit discovery toolkit (Metasploit, Nuclei, GitHub & more)
Swaggervu
A simple, evidence-first Swagger/OpenAPI security workbench with a policy-bounded MCP server.
AegisForge MCP
Zero-trust AI security research engine built on MCP, Tauri v2, and Rust — with prompt injection defense and sandboxed tool execution
Ghidra MCP WSL Auto
One-click deployment of Ghidra + GhidraMCP (Model Context Protocol) on WSL2 — AI-assisted reverse engineering for security researchers
Domainlooker
A fast CLI and MCP server for inspecting domains — WHOIS/RDAP, DNS, SSL, ports, subdomains, and DNS propagation — with CSV/JSON export.
Lucinlabs
Static analysis for AI agent tools. Reads the function body, not the tool description.
Hive Agent Framework
Multi-agent coordination framework with persistent shared memory and MCP integration
Yteam
Local-first, policy-bound security research workbench with an OpenCode-style TUI, durable jobs, adaptive planning, LocalSolver, and read-only MCP.
Tool Poisoning Toolkit
Demonstrates MCP tool poisoning (malicious tool descriptions/schemas) with a runnable vulnerable server + a detection scanner. Includes real captured example output.
Scrapeless Browser Instrumentation
Stealth Chrome DevTools Protocol instrumentation for reverse-engineering hostile client-side JavaScript — anti-bot, captcha, fingerprinting and payment SDKs. Invisible hooks, capt…
Agent Honeypot
Defensive deception framework for autonomous LLM agents: synthetic MCP tool servers, 24-dimension fingerprinting, digest-only capture, counterexample-driven lure evolution, audite…
GDB AI
Stateful GNU GDB interface for AI agents: MCP and JSON-RPC APIs, Python/TypeScript SDKs, and Linux user-space and kernel debugging.
Mac Bridge MCP
An MCP server that lets an AI securely control a macOS machine over the network. Run shell commands, transfer files, and test binaries from any client, on any OS.
Mrholmes Osint Suite
SSG REAPER OSINT kit — authorized research CLI, GUI, and MCP
Codex Tripwire
Live audit and observability for Codex CLI - commands, network policy decisions, MCP calls, and Web Search activity.
Http Bait
An HTTP honeypot built to measure exploitation rather than discovery: attributable honeytokens, a shared detector table, and a reproducible offline analyzer.
Open Agent Bounty Kit
Modular, agent-agnostic bug bounty workspace for AI-assisted security research. Two kits in one: Claude Code (CLAUDE.md) and model-agnostic (AGENTS.md) for OpenCode, Muse, DeepSee…
Workers Honeypot
A Cloudflare Workers + D1 multi-skin honeypot for defensive security research, attack telemetry, credential-pattern analytics, and live threat visualization.
Claude Code Decompiled
Explore research reports on Claude Code v2.1.88 covering architecture, agent behavior, permissions, prompts, MCP, and context management
Agent Skills State 2026
Study of 2,999 public agent skill, plugin and MCP repositories (October 2026): missing security policies, unpinned MCP servers, unrestricted shell in skills, front matter that fai…