- 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.
Read Only SQL
Secure MCP server providing read-only SQL access to PostgreSQL and ClickHouse databases
Guardrails
Enterprise-grade security gateway for Model Context Protocol (MCP). Multi-layered protection with DLP, UEBA, policy-based access control, and comprehensive audit logging for AI as…
Adk Simple MCP Demo With Armour
Google ADK + MCP server with security armour: prompt injection defense & hallucination guardrails
Contract Validator MCP
MCP server for smart contract vulnerability analysis, gas optimization, and security auditing
Malwar
Static analysis engine for detecting malware in agentic AI skill files
Agentic Iam
Secure, Agentic Identity and Access Management (IAM) platform with Next.js, Node.js, and Model Context Protocol (MCP) integrations.
Sentinelqa
Playwright-native release-confidence engine for LLM-built and human-built web apps. Quality scoring, CI gates, MCP tools, Python SDK.
Agentperms
Least-privilege permissions for AI agents and MCP tools. Record what your agent does, auto-generate a safe policy, and block dangerous tool calls before they happen.
Cloudledger
Multi-account AWS security scanning and infrastructure ledger with Prowler integration, taggable scan history, multi-backend storage (SQLite, PostgreSQL, MySQL, MSSQL), and an MCP…
Sample App
FastAPI sample app built on delego — intent-bound action authorization for AI agents
Claude Glm Wrapper
Secure wrapper to use Z.ai GLM models (GLM 5, 4.7, 4.6) with Claude Code - credential protection, session isolation, automated secret scanning
Safety Scanner
Dependency-free CLI + GitHub Action to scan JS/TS repos for MCP/tool-server security footguns (CORS, eval, exec, etc.)
Rigscore
Configuration hygiene checker for AI dev environments. Scans locally, no external calls.
Splunk SOAR Playbook Lab
Validate SOAR playbooks against BOTS v3 evidence using Splunk MCP, MITRE ATT&CK, VirusTotal, and approval-gated dry runs.
Deos Mcpd
Governance proxy for MCP servers — permits, receipts, audit trail.
Threatmod AI
AI-powered security threat modelling pipeline — STRIDE analysis via LLM, AWS control verification via MCP, two-stage approval workflow, GitHub + Confluence publication.
Autopentest MCP
Capability-gated MCP-style tool server for pentest agents: four gates (capability, scope, policy, run) the agent cannot exceed, plus a tamper-evident hash-chained audit of every c…
Agentdiag
Read-only diagnostics CLI for Hermes Agent and Oh My Pi (OMP): inventory skills, plugins, and MCP configuration; export sanitized support reports.
Dvah
DVAH — Damn Vulnerable Agent Harness: a patch-the-runtime security lab for AI-agent platforms. Exploit a real architectural bug, trace it, patch the harness, and prove the securit…
Tabgrant
User-granted, local-first browser capabilities for AI agents.
Steward
Open-source identity & access governance for AI agent fleets — effective-access analysis, segregation-of-duties, least-privilege enforcement, and a tamper-evident audit ledger.
MailForAI
Give an AI agent its own mailbox — recipient allowlist, daily cap, and an auditable history. No dependencies, MCP built in.
Handoffprobe
Open-source security testing for A2A → MCP agent handoffs and cross-protocol AI agent systems.
Praetor Security
Multi-engine static security analysis for code, repos, and AI agents: SAST, secrets, SCA, AI-security, and serialized-model/pickle scanning. Reports attack CHAINS and an agent cap…
Runreveal
RunReveal — independent third-party profile of a public API surface, by API Evangelist. RunReveal is a unified security log management and detection platform that replaces traditi…
Clawvisor
Clawvisor — independent third-party profile of a public API surface, by API Evangelist. Clawvisor is the authorization layer for AI agents — a Y Combinator (Spring 2026) security…
Mincode Vuln Arch
Minimal code generator + vuln auditor + architecture miner with a tamper-evident hash-chain vault. Zero deps. Agent-agnostic (CLI / pip / pyz / MCP / AgentSkills).
AI Pentest Agent
基于 LLM Agent + MCP 的自动化安全侦察框架：自然语言驱动 nmap / subfinder / httpx，完成子域枚举 → Web 探测 → 端口扫描 → 中文报告闭环（仅限已授权场景，只做侦察不做利用）
Repo Canary
Preflight any repo before your AI coding agent trusts it. Local scanner for agent instructions, MCP, hooks, and permissions.
CanaryNorth
Secretless MCP policy proxy with scoped capabilities and tamper-evident receipts
Awesome Agent Security
A curated list for securing autonomous AI agents — configs, runtime, tools, MCP, and red-teaming
K8s Agent Secrets Hardening
Which Kubernetes controls actually protect an agent's LLM credential. RBAC, restricted Pod Security and token automount all on, and one file read still yields the key.
Agent Governance Toolkit
Manage and monitor AI agents in production environments with tools for governance, safety, and compliance.
Ecpunk
Jon Woodall — Principal Sales Engineer. Agentic AI security, governance, and operator tooling.
Eufy Lock Codes
Safety-first Node.js tooling for reviewable, verifiable smart-lock access-code operations.
Public Portfolio MCP
Read-only MCP-style JSON-RPC portfolio service with strict schemas, security tests, Docker, and CI.
Consentinel
Static security auditor for MCP servers. Finds tools that can do irreversible or external damage and verifies each one actually enforces a human-in-the-loop safeguard — not just d…
Task Runner
MCP server to run & schedule shell tasks safely (allow/deny list, no shell, timeout). Controlled 'remote hands' for AI agents.
Corex Manager
Control plane, data plane, and web GUI for HAProxy — load balancing, TLS, WAF, caching, and API security
Intermcp
Ultra-fast, safe Model Context Protocol (MCP) engine and multiplexing hub in pure Rust, built for Interlayer Blockchain and open for all
Os Loop Bridge
Native companion for OS Loop AI that extends browser agents with secure local capabilities—filesystem access, MCP connectivity, long-running tasks, and system-level execution
M Gate
MongoDB powered MCP Gateway. A multi-tenant MCP (Model Context Protocol) gateway with auth, RBAC, guardrails, a WASM code sandbox, queryable encryption, and observability.
Hackmonty
Autonomous Sandbox Security Assessment
VulnerabilityIntelligenceMCPServer
⌛In progress | A server implementing MCP exposes vulnerabilities in real time.
Openvuln MCP Server
An Model Context Protocol (MCP) server for Cisco Security Advisories
Cylera MCP Server
The official MCP Server from Cylera. Brings context about device inventory, threats, risks and utilization powered by the Cylera Partner API into an LLM.
Ntm
The official MCP server for Threat Manager.
Owasp Asvs MCP Server
MCP server for OWASP Application Security Verification Standard (ASVS)
CISA Threat Intelligence MCP Server
Use a MCP server to know about Cisa CVE's
Lawmatics MCP Server
Model Context Protocol server for the Lawmatics OAuth API