- Conduid
- Marketplace
- #security
MCP servers tagged security
4.9K 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.
Docker
Govern consequential AI agent actions in Docker with deterministic policy, human approval, and signed Decision Dossiers.
Shodan
MCP server for Shodan — search internet-connected devices, IP reconnaissance, DNS lookups, and CVE/CPE vulnerability intelligence. Works with Claude Code, Codex, Gemini CLI, and C…
Fairquery
Fairquery profile: precise, agent-ready APIs and MCP tools.
Www Project Agent Memory Guard
OWASP Foundation web repository
Server
NotCVE MCP server — live vulnerability intelligence for AI agents: 365k+ CVEs/NotCVEs, CVSS, EPSS, CISA KEV, affected versions, exploits and patches from 80+ sources.
Dockhand MCP
Security-first MCP server for DockHand
Lint
Static security linter for MCP tool definitions — catch prompt injection, tool poisoning & unconstrained schemas before your agent loads them
Scanner
Security auditing tool for MCP (Model Context Protocol) servers — 27 checks, web dashboard, SARIF output, compliance mapping
Security Scanner MCP
MCP server for Nuclei vulnerability scanning with cluster integration
FinMCP
Production-grade MCP server with OAuth 2.1, elicitation, OTel observability, and self-scanning security controls. Reference implementation for AI agents over financial data.
Warden
Self-contained MCP proxy for safe agentic tool access with policy enforcement, secret management, and browser automation.
Risk
Pre-install and config risk checks for MCP servers and agent tools.
Gateway
Security proxy for MCP servers — auth, logging, rate limiting, monitoring. The Datadog of MCP.
Noctua
MCP server exposing a sandboxed pentest toolbox (sqlmap, nuclei, ffuf, httpx, naabu, katana…) to an LLM orchestrator, for authorized security audits
Query
Secure local MCP server for Claude Code — query databases with Apple Keychain credentials, granular SQL permissions, and full audit logging.
Mcpscan
MCP production-readiness audits and local security scans for Model Context Protocol servers.
Decoy
Deterministic mcp decoy service with forensic dashboard
Shield
Static risk scanner for Model Context Protocol (MCP) server configurations.
Audit
Python security scanner for Model Context Protocol (MCP) servers — find prompt injection, over-broad permissions, weak input validation, and credential leaks before your AI agent…
Securing MCP Servers
Notes and exercises for the O'Reilly live course: Securing MCP Servers — exploitation and defense of Model Context Protocol implementations.
Shield
🛡️ MCP Server Security Auditor & Trust Dashboard — Scan, audit, and visualize your MCP server attack surface with trust scores (A-F), Rich CLI, and glassmorphism HTML reports
Mcpauth
Drop-in token-auth gateway in front of unauthenticated MCP servers
Mcpvet
MCPVet — scan MCP servers, Claude Code skills & plugins for unsafe behavior before you install them. One-step MCP server + skill. https://mcpvet.com
MCPGuard
MCPGuard is the open-source CI gate for MCP servers — it tests protocol compliance, scans for security vulnerabilities, validates tool behavior, and benchmarks performance before…
Mcpcheck
Correctness checks for MCP servers — prompt-injection lint, contract drift, over-broad tools, dishonest annotations. Never calls a tool.
Agentgate
The open-source firewall for AI agents.
Mcpscan
Zero-dependency CLI: inventory MCP server configs across every AI client, detect drift, flag supply-chain risk, and measure context-token cost per server
Lint
Static and live-protocol conformance linter for MCP servers -- audit tool schemas, docs, tests, security posture, and protocol conformance before you ship.
Shodan
MCP server for Shodan — search internet-connected devices, IP reconnaissance, DNS lookups, and CVE/CPE vulnerability intelligence. Works with Claude Code, Codex, Gemini CLI, and C…
Sec Audit
Static analysis for Spring AI MCP servers: finds @Tool methods exposing risky capabilities without authorization
Agent Tool Gateway
An engineering agent whose tools sit behind three access designs (shared key, forwarded user token, gateway with per-tool scopes and approvals), compared with fifteen executed att…
Red Team
mcp security scanner. mid-2025. deprecated.
Audit
See what your AI agents can access. Scan MCP configs for exposed secrets, shadow APIs, and AI models. Generate AI-BOMs for compliance.
Sevlex MCP Gateway
Layer 7 Zero-Trust Security Gateway & Control Plane for the Model Context Protocol (MCP).
Awesome MCP Security
An opinionated list of awesome MCP(Model Context Protocol) security
040 Connected Services MCP Hub
A secure MCP hub connecting ChatGPT to private business services and operational data.
Unifi Protect MCP
MCP server for UniFi Protect surveillance - cameras, sensors, lights, and security monitoring
Keygate
面向 AI Agent 的零信任凭证网关 - 让 AI 安全访问 API，密码永不进入 LLM 上下文
Security Gateway
Local-first MCP security gateway for policy-checking tool calls, risk scoring, approvals, and audit trails.
Agenticqa Scan Action
Analyze AI codebases to identify integration points, security risks, and test coverage gaps in one step with comprehensive reports.
Seclog
Self-hosted web log security dashboard: ingests access logs, flags suspicious activity, and exposes the data to LLMs through an MCP server.
JARVIS HUB24
Open-source tools for automation, developer workflows, and AI integrations
Agent Scope Diff
Risk-focused diffs for agent manifests, MCP configs, and tool permission snapshots.
Agentbond
Zero-trust capability delegation for MCP multi-agent systems. Solves the confused deputy problem with scoped JWT tokens, deterministic enforcement, and full audit trail.
Agent Cordon
Zero-dependency prompt-injection and data-exfiltration firewall for LLM agents: scans untrusted text and outbound actions, sees through obfuscation, guards the MCP/tool boundary.
Canary
Which fields of an MCP tool result actually reach the model's context, measured with benign canaries across every installed server
Agent Security
Skills for coding agents that audit and harden other agents: SSRF gate audit, threat model for agentic spend, MCP visibility audit, signed audit log. MIT.
Agentveil
AgentVeil: a privacy-first, fail-closed browser built for AI agents (MCP server: search, fetch, hardened Firefox, E2E agent messaging)
Agent Vault
A local credential proxy for coding agents: the agent sends a placeholder and never holds the secret. Free and open source from ioLite Labs.
Signalshield
Evidence-first trust scanner: paste claim + sources, get risk signals, evidence gaps and a shareable receipt. MIT.