- 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.
Hermes Security Suite
奇点造物 Genesisix-hermes — Agent安全三件套。检测(825规则/13层)+诊断(自愈)+防护(实时拦截)。
Piedpiper
Pied Piper for real — end-to-end encrypted P2P chat + federated comms protocol. No signup, no server that owns your data.
Moat
Verified Agent Capabilities Marketplace — MCP-first trust + policy + execution layer for agents
PROJECT ARGUS
Local-first security evaluation and runtime policy gateway for AI agents, MCP servers, skills, and LLM deployments
Agentsid
Identity, permissions, and audit for AI agents. The Auth0 for the agent economy.
Project R Score
A comprehensive development ecosystem featuring enterprise-grade tools, automation frameworks, and performance optimization utilities built with Bun and TypeScript.
Broude
Your AI coding assistant's security watchdog. Claude Code hooks that catch supply chain attacks, exposed secrets, and obfuscated commands.
Verdict
Autonomous DFIR agent for SIFT - cited findings, audited actions, zero hallucinated evil.
Secretbroker
SecretBroker is a local macOS credential broker for scoped, user-approved AI agent operations without exposing stored credentials.
Threatlocker MCP
MCP server for ThreatLocker — zero-trust application allowlisting, approval requests, audit logs
Tkach Security
Fail-closed MCP adapter for untrusted model output over a local Tkach runtime.
Devassets
The local-first secrets manager and credential command center for independent developers — CLI + MCP server
Vaultbridge
Secret management for AI coding agents. Your secrets never enter the LLM context window.
Bounty Hunter MCP
Give your AI superpowers for bug bounty hunting. MCP server that turns Claude Code into a structured bug bounty toolkit — recon, live testing, intelligence, and report generation.
Fbrcm
Terminal manager for Firebase Remote Config
Hermes Shield
Input sanitizer for AI agents — anti-prompt-injection shield
Ssl Check MCP
SSL certificate checker via MCP. Issuer, expiry, SANs. Free + $19/mo.
Planka MCP Server For Claude
MCP server connecting Planka Kanban boards to Claude for AI-powered project management
Niiko MCP Server
The remote MCP server of niiko — connect Claude or any OAuth-capable MCP client and every action you grant becomes a tool.
Cli2mcp Gateway
Wrap any CLI as a Streamable HTTP MCP server with bearer / OAuth 2.1 / Auth0 auth
Tool Sanitizer
Detect and neutralize Unicode concealment codepoints in MCP tool metadata (covert-channel control). AGPL-3.0-or-later.
Fsck
Integrity check for MCP server configs audits Claude, Cursor, VS Code and Windsurf agent configs for secrets, injection-prone args, tool poisoning and dangerous capability combos.
Sentinel Osint
Unified AI-Native Intelligence & Anti-Scam Platform (Tauri v2, Rust, React, MCP)
Minesweeper For AI
Spectator-only Minesweeper with an authenticated API for AI agents.
Mimir Scan
An MCP security scanner that integrates with AI coding agents like Claude Code, GitHub Copilot, Cursor, and others.
Policy Testkit
CI-first policy and security testkit for MCP servers, manifests, metadata, and source artifacts.
Java Sentient MCP
Giving AI Agents a Developer's Soul for Java. An MCP server that empowers LLMs with IDE-level consciousness via Eclipse JDT.LS. (为 AI Agent 注入开发者的 Java 灵魂。通过 JDT.LS 让大模型具备 IDE 级别的…
Bayesoutputgate
Calibrated output validation with the Bayes Factor: weigh per-dimension quality scores into a pass, fail, or escalate decision on the Jeffreys scale, not an arbitrary threshold. Z…
Skillguard
Static security scanner for AI agent skills and plugins — flags prompt injection, hidden Unicode, exfiltration, and dangerous commands in SKILL.md/CLAUDE.md and scripts.
Accessibility Suite
Unified monorepo for accessibility testing, evidence generation, and WCAG compliance tooling
ZugaShield
7-layer AI agent security system — stop prompt injection, data exfiltration, and AI-specific attacks in under 15ms. Zero dependencies.
Veyra Commit Core
Landing page and public docs for Veyra, the commit mode layer for production AI agent actions.
Ursa
An AI first penetration testing toolkit ✨
Markdown Everything
Privacy-first local context inbox for traceable Markdown, Obsidian vaults, and agents
Radiochron Electron
Windows desktop client for RadioChron: Wi-Fi diagnostics, local network inventory, evidence timelines, and run-to-run comparison, on the pure-Rust radiochron MCP engine.
Gmail MCP Send To List Only
send to list only gmail MCP for VPS
Burp Autopilot
Drive Burp Suite autonomously from the CLI — MCP-transport client + companion Montoya extension for scans & scripted fuzzing
Symaira Brain
🧠🔐 Portable agent-context layer — multiplexes vault, memory, and skills behind one MCP gateway for AI coding harnesses.
Dsh Shield
Security, Trust & Policy Layer for DeepSeek Harness. Don't trust your agent's tools. Verify them.
Checkpoint MCP Server
Governed Model Context Protocol server for Check Point R82 firewall management — RBAC, human-in-the-loop approval, tamper-evident audit.
Paseo MCP
Manage MCP servers, OAuth, and project connections from Paseo
Splunk MCP Security
Splunk Security MCP Server with behavioral threat hunting capabilities.
Hermes Plugin Snyk
Hermes Agent plugin: Snyk code/dependency/container/IaC scanning via Snyk's first-party MCP server, with the snyk-security-scan skill bundled (Agent Plugins v1)
Agent Extension Auditor
Local-first security auditor for AI agent skills, plugins, MCP servers, hooks, configs, and packages.
Uipath Orchestrator MCP Python
Python MCP server for UiPath Orchestrator — typed async client with multi-auth support for managing automations through Model Context Protocol
Frevo MCP
F-revoCRM(vtiger) を Model Context Protocol (MCP) 経由で Claude などのAIから操作するモジュール。OAuth 2.1 + Bearerトークン認証対応。
ReconPal
Friendly recon and configuration-audit tool for authorised security testing, with Model Context Protocol (MCP) deployment discovery
Gmail Oauth
Self-hostable Gmail MCP server with stdio downstream OAuth and OAuth 2.1 Streamable HTTP
Mahrem
Local PII masking for Turkish documents — MCP server and skills for AI assistants. MIT licensed.
Orknux Shell
MCP Server for operating system access, integrates seamlessly with Orknux Server