- Conduid
- Categories
- Security
Security MCP servers
Security MCP servers indexed by Conduid, ranked by trust score. 4.9K live listings from GitHub, npm, PyPI and the official registry, each with a 0–100 score, security checks, and install commands.
AgentDefense Bench
A comprehensive security benchmark for evaluating infrastructure-layer defenses in MCP-based AI agent systems
ShellWatch
Passkey-backed SSH for humans and AI agents
Awesome Agent Vault
The category map for agent credential management. Products, integrations, recipes, patterns, threat models. Curated by Authsome.
Verdict Dfir
VERDICT — a DFIR agent (Claude Code as the engine) that produces a signed, offline-verifiable verdict. SANS Find Evil! 2026.
MasterVault
An orientation protocol for LLM sessions — plus a curated Claude skills collection
Kali Opencode Usb
Bootable Kali Linux USB with AI-powered pentesting: OpenCode, CLI Agent, Kali MCP (35+ tools), and Shannon Plugin (autonomous pentesting with 600+ Docker tools). Boot anywhere, pe…
Audit A Static Security And Hygiene Audit CLI For MCP Servers
A CI-friendly open-source CLI that statically audits MCP servers before they are wired into AI agents. It flags tool poisoning, hidden Unicode payloads, misleading annotations, an…
Calendar Autoauth MCP Server
A Model Context Protocol (MCP) server for Google Calendar integration in Cluade Desktop with auto authentication support. This server enables AI assistants to manage Google Calend…
Delphi Visual Studio Code Debugger
A debugger for delphi in visual studio code, and also a MCP server to give claude/copilot/etc authonomous delphi debugging capabilities
Sb Siem MCP
sb-siem-mcp is an MCP server that connects LLMs (like Claude) to Wazuh SIEM, enabling natural language threat hunting, alert analysis, compliance checks, and incident response thr…
Windows Memory Forensics MCP
MCP server for Windows memory forensics. Provides AI agents with 33 tools for analyzing memory dumps using Volatility 3, MemProcFS, and CLR/SOS backends. Includes process analysis…
Fortianalyzer MCP
MCP server for FortiAnalyzer JSON-RPC API. Query logs, alerts, incidents, FortiView analytics, and PCAPs from AI assistants.
Accuretta
A sovereign, zero-trust local AI agent and micro-IDE.
Nuwaclaw
nuwax agent
Tabby AI Assistant
Tabby Terminal AI Assistant Plugin - Multi-AI provider support with smart command generation and security features
Universal MCP Oauth
Universal MCP IdP (Identity Provider) - Support Thousands of Integrations, Zero Maintenance
Safesemantics
SafeSemantics is a topolgical guardrail for AI apps and agents. Just plug and play the security layer of AI with advanced knowledge base of how all attackers penetrate and exfiltr…
Brin CLI
the credit score for context.
Smith Core
The most secure AI agent. Live the automation dream without the security nightmares.
Cursor MCP Trivy
A Model Context Protocol (MCP) server that provides Trivy security scanning capabilities through a standardized interface.
Web Security Agents
LLM Agents for Web Security
Awesome Legal Tech
A compilation of useful software, repos, and apps for lawyers and legal tech developers.
Malshark
AI-powered malware traffic analysis and network forensics via the Model Context Protocol
Sample MCP Security Scanner
This pattern describes how to implement a Model Context Protocol (MCP) server that integrates three industry-standard security scanning tools (Checkov, Semgrep, and Bandit) to pro…
Cybersec
Empowers the AI to perform penetration testing, vulnerability assessment, reconnaissance, and security reporting — all through natural language conversation.
GAIA Obsidian Vault
GAIA Obsidian Vault
Threatshield
Making lives of Security Engineers easier!
TEA Bench
[ACL 2026] TEA-Bench: A Systematic Benchmarking of Tool-enhanced Emotional Support Dialogue Agent
Kali Burp MCP Bridge
kali-burp-mcp-bridge is a Model Context Protocol (MCP) server that gives any AI assistant (Claude, ChatGPT, Cursor, and more) direct access to your Kali Linux security toolchain a…
Pentest AI Killer
Pentest AI Killer
Opencode Puter Auth
OpenCode plugin for Claude Opus 4.5, GPT-5, Gemini via Puter.com — 500+ models, automatic fallback, no API keys.
Gitscape.ai
Scan any agent skill — authored or compiled — for prompt injection, secrets, and malicious execution before it touches your agent. Or compile the long tail on the fly.
CloakLLM
Open-source PII cloaking + tamper-evident audit logs for LLM API calls
OllamaClaude
An MCP server which allows Claude Code to use a local Ollama server for tasks.
Rechtsinformationen Bund De MCP
An MCP (Model Context Protocol) server that provides access to the official German Federal Legal Information Portal (rechtsinformationen.bund.de). **Claude Desktop will automatica…
Trustmodel
Score any AI for trust — Eval, Monitor, Govern. 10 trust dimensions, one free API key (5 credits / $500).
Quell
Stop API keys and passwords leaking into AI tools. Offline secret detection and redaction for VSCode, Cursor, Windsurf, and Claude Code.
Dw MCP AI Permission Center
基于 RBAC 的 MCP（Model Context Protocol）权限管理中心，为 AI 客户端提供动态工具列表与数据访问控制。
Openclaw Security Monitor
Proactive security monitoring for OpenClaw deployments. Detects ClawHavoc, AMOS stealer, CVE-2026-25253, memory poisoning, and supply chain attacks.
Nextr4y
Golang tool for Next.js reconnaissance - uncover build IDs, routes, and assets with bot management evasion.
Owl Portability Layer
Vendor-neutral OWL/SHACL semantic layer for enterprise AI platforms
Claude Guardrails
Hardened security configuration for Claude Code; permission deny rules, shell hooks, and prompt injection defense in full and lite variants.
Hack3270
hack3270 is a python3 based tool to manipulate tn3270 data streams, specifically to perform application penetration testing of mainframe CICS applications.
Itylos CLI
🦋 ITYLOS : L’art de l’éphémère numérique. Outil de messagerie souverain avec chiffrement local AES-256, protocole Double-Shield et auto-destruction physique après lecture. Reprene…
Ddos Attack Script Demo
仅用于授权情况下验证安全产品的抗DDoS能力，请不要在未经网站所有者同意的情况下进行攻击。
Rafter CLI
Multi-language CLI for Rafter — the security toolkit built for AI coding agents and the developers who use them.
Context Firewall
Local-first context firewall for coding agents
SocialHackAPI
A vulnerable social media API designed for practical API security training. Built according to the OWASP API Security Top 10 standards.
Product Pipeline Public
Run a product initiative as a tracked journey — not a toolbox of one-shot answers. Persistent state, living PRD, evidence-typed hypotheses.
Eresus Sentinel
AI/LLM security scanner — model artifact analysis, prompt injection firewall, MCP agent validation, pickle/safetensors/GGUF fuzzing. Zero false positives.