- Conduid
- Marketplace
- #security
MCP servers tagged security
4.8K live MCP servers tagged "security", ranked by trust score. Tags come from package metadata and repository topics, so this list covers servers across every category that work with security.
Bounded Agent Runtime
Security runtime for AI coding agents: bounded authority, exact-candidate evidence, separate review and human gates. Works with Codex, Claude and OpenCode.
Clayseal Receipts
A signed record of what an agent asked for, what policy said, and what happened.
Polisafe
Polisafe is a complete, self-hosted Identity and Access Management (IAM) platform: an OAuth 2.0 / OpenID Connect provider, a multi-tenant RBAC (roles–permissions–scopes) engine, a…
Sentinel Code Agent
Autonomous security & code review agent - free, local-first, diff-aware. Rule + Bandit + Ruff detectors, LLM explanations via Ollama or any OpenAI-compatible model, validated…
PCAP Analyzer
AI-powered PCAP analyzer with MCP: natural-language flow analysis, QUIC/TCP/UDP detection, and threat insights.
Hyprland Computer Use
Hyprland computer-use MCP server with Quickshell permissions and compositor-scoped input
Nfi Tools
CLI tool and MCP server for handling sensitive information without exposing values to AI assistants
Akko MCP Trino
Governed MCP server for Trino — every tool call carries the user's identity; the engine decides. Any OIDC provider, any MCP host, any model.
Aeontra
Scoped, auditable MCP tools that let ChatGPT and coding agents work with operator-controlled repositories and signed local Edge hosts.
AI Skill Create
AI Skill Create: toolkit for creating, validating, testing, and packaging reusable AI agent skills and Codex skills.
Keelix
Local-first security scanner for self-hosted infra — host, containers, services, and AI-agent/MCP posture. Don't ship with a hole in the hull.
Adtp
Cryptographic identity and delegation for AI agents — UCAN chains, RESTRICT mode (structurally impossible escalation), provably-complete cascade revocation. Single Go binary. Apac…
Agenticqa Scan Action
Analyze AI codebases to identify integration points, security risks, and test coverage gaps in one step with comprehensive reports.
Mvsd AI Skills
Deploy discrete, purpose-built AI skills for Claude and other SKILL.md-compatible agents to automate focused, recurrent workflows.
Winbox
Isolated Windows vulnerability-research platform for Kali and AI agents: VM automation, hypervisor debugging, driver/IPC testing, containment, and MCP.
Security Gateway
Local-first MCP security gateway for policy-checking tool calls, risk scoring, approvals, and audit trails.
Joern Agent Bridge
Bounded Joern CPG tools for Codex and MCP coding agents
Claudepass
Secret manager for AI coding agents. Agents see Handles, never Secret values.
AutoJs6 Plugin MCP Server
MCP Server plugin for AutoJs6: authenticated device automation through Model Context Protocol
5arz Proof Of Human
Prove a real, unique human performed an action; mint a signed, verifiable Proof-of-Human credential. MCP server for agents.
Trutu Photo Verify MCP
今日水印相机照片验真 MCP Server - OpenClaw Skill for photo authenticity verification
Ghost MCP Fusion360
A zero-trust Model Context Protocol (MCP) server for Autodesk Fusion 360.
Keycloak Guard
Reference MCP server that authorizes every tool call against Keycloak realm roles — per-tool RBAC, not just authenticated/unauthenticated.
Office Reporting MCP Kit
Reusable MCP contract, Agent Skill, and Python adapter kit for safe backend-authorized Office report generation and delivery.
Security Gate Cursor
Three-layer security for Cursor: rules, evidence-grounded planning, MCP handbrake, KEV/OSV intel, Docker scanner lab
Legant
Open-source delegated authorization for AI agents — RFC 8693 on-behalf-of tokens, offline-verified constraints, monotonic attenuation. Single Go binary, self-hostable.
Identark CLI
Command-line client for IdentArk credential references, approvals, and managed access for AI agents
Quilzo
Immutable, content-addressed CMS with an agent interface that enforces a manifest — capabilities, content scope, budget, and the tools it may call on hosts it named first. Publish…
Dracula
Local-first reverse engineering and runtime analysis workspace for Windows.
Jcyber
Agent-driven bug bounty / pentest framework: one gated chain over five systems (Caido, HexStrike, Jev, Memgraph, TencentDB, Prometheus)
Agent Hardening Guide
Production hardening guide for AI agents — prompt injection defense, tool sandboxing, and credential management
Nexus Web ChatGPT
A secure local MCP bridge for connecting ChatGPT and AI agents to explicitly authorized local development projects.
Mcpdef
A fast, self-hostable, single-binary MCP gateway & governance plane in Rust: multiplexes MCP transports, enforces a deny-by-default allowlist + RBAC, brokers auth, sandboxes untru…
Firelin
面向 AI Agent 的授权网络评估工具集 — TCP 端口扫描 / DNS 子域枚举 / 目录爆破 / HTTP 指纹识别，JSON in / JSON out 并附 MCP 服务（BIT 生态）
ADONWORD
智能体主动防御哨兵 — 文件完整性基线 / 可疑进程监控 / 监听端口告警，BIT 生态内可独立运行的 Rust 守护进程
Solsentry MCP
Zero-install MCP server for SolSentry — Solana operator threat intelligence for AI agents. NPM: @solsentry/mcp
Provio
A safety floor your AI agents can't get under: one policy for Claude Code, Codex, Gemini CLI, Cursor, Windsurf and MCP, judged by what each call will run, backstopped by the kerne…
Rustmachineguard
AI-agent posture scanner for developer machines: inventory, sourced threat catalog, live MCP probing, scan diffing, CycloneDX 2.0 Blueprint, compliance evidence. Local only. Not a…
Hermes Sentinel
Hermetically-sealed secret protection and capability execution MCP for AI tools
Guard Scanner
🛡️ Agent Security Scanner — 364 patterns, 35 threat categories, 27 runtime checks. Zero-Trust policy layer for MCP/A2A agents.
Watchcheck
Read-only MCP server + live panel to detect & explain endpoint monitoring (EDR/DLP/MDM) on macOS, with first-class coverage of Chinese enterprise agents.
Stoneburner
Local-first LLM eval: cost, quality, and security suites. Install stoneburner-atomics; CLI is atomics.
Obsidian Next
A professional, structure-first AI agent interface for the terminal. Features strict typing, auditor-enforced security, and a Supervisor-Agent topology for safe, autonomous execut…
ASI4 Labs Demo
ASI04 Supply chain vulnerable lab based on OWASP Top 10 for Agentic Apps
Enlil
Source-available control and audit plane for AI agent actions. Enforce what your agents may do, and prove what they did.
AI Agent Firewall
Local-first security firewall for autonomous AI coding agents — intercepts, risk-scores, and human-approves every tool call (Claude Code / Codex / Cursor / Cline). Apache-2.0.
Deadbolt
Local admission gate for software agents. Rust, HTTP and stdio MCP integrations with policy, operator revocation and structured evidence.
Epoch Software.evolution
EPOCH: the control and intelligence plane for software that never stops changing. IBM Bob drives governed changes through MCP; EPOCH measures trajectory, drift, invariants, incide…
Stateless Threats
Deliberately vulnerable local threat lab for Stateless MCP, Stateful Trust at MCP Dev Summit Toronto: task authorization, tenant boundaries, and cancellation evidence.
SKILL DEY Enterprise Agentic Framework AI Development Suite
🚀 Ship AI-assisted code that doesn't break your app. Agentic quality framework: zero-error delivery, undo, execution guardian, project memory, multi-agent review & MCP server. By…