- 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.
DevGuard Enterprise
DevGuard Enterprise — AI Security Platform powered by DataHub. Autonomous AI agents for security analysis, graph reasoning, evidence-driven remediation, and enterprise governance.
Agent Authz
Secure-by-default authorization PEP for APIs, Agent tools, RAG, and tasks
TailorLayer
Evidence-first security review for agent repositories: source-linked findings, suggested fixes, drift checks, and least-privilege launch plans.
Skill Tripwire
A fail-closed scanner for poisoned agent skill and config files. Zero dependencies, published detection and false-positive rates.
Akasha
A local vault for AI agents — credentials your agents can use but never read, with a full audit trail. Local-first, Apache-2.0.
Tailgate
Securely serve local MCP servers to the public internet using Tailscale Funnel and OAuth
AI Shield Py
Python LLM security middleware: prompt-injection, PII, tool-policy, cost-budget, audit. Port of ai-shield-core (TS).
Obsidian MCP Ana
Plugin Obsidian: ponte MCP (servidor + cliente) para integrar o vault ao Claude e a servidores MCP externos (Projeto ANA / PJe TJMA).
Margins Oracle
The fairness oracle for India's 63M shopkeepers — multimodal agent + MCP server, built on Gemini.
Guardskill
Read-only scanner for what lets a repository run code in a coding agent (Claude Code, Codex, Cursor, Copilot): git settings, hooks, and committed MCP server definitions and agent…
Publii MCP
Model Context Protocol (MCP) server that enables AI assistants like Claude to manage Publii CMS websites – create, read, update & delete posts, pages, tags and authors
EspoWoah
A Model Context Protocol server that lives inside EspoCRM. One endpoint on your existing CRM URL, every tool call running with the authenticated user's own ACL — and a setup flow…
O11ystack
Observability & AI Stack with VictoriaLogs, VictoriaMetrics, VictoriaTraces, Grafana, LiteLLM, MCP Servers, and OpenTelemetry
RScrapper
Free internet access for your coding agent — Rust toolkit that turns any URL into clean, LLM-ready Markdown (CLI + HTTP API + MCP server + dark web OSINT).
Mpak Trust Framework
MTF: An open security standard for MCP server bundles. Defines compliance levels, controls, and verification methods.
Crackq
Self-hosted password cracking queue — multi-user hashcat with audit log
Pcapsummary
Summarize flows/talkers/protocols from a pcap text export
Privacyshell
Hardened browser profile generator — Firefox / LibreWolf / Brave
Xdr MCP
MCP server for the F6 XDR platform — gives AI assistants access to alerts, incidents, mail, files and hosts
SOC Sentinel Splunk
Agentic SOC analyst for Splunk — Claude investigates via the Splunk MCP Server; a deterministic 3-layer validator verifies every finding against real data. An anti-hallucination t…
Evm Agent Toolkit
Deterministic MCP toolkit for autonomous AI agents auditing and optimizing EVM smart contracts
Governance Kit
Runtime capability-state attestation for MCP agents. Companion implementation to the paper 'The MCP Governance Gap' (Teklenburg, 2026).
Cloison Runtime
Multi-tenant AI agent runtime with OS-level isolation. Sandboxed execution, encrypted credentials, private memory per tenant — one server, no Docker.
Vor Commander
Agente local y gateway MCP para Windows: acceso controlado de asistentes de IA a tu PC, con aprobaciones firmadas, auditoría a prueba de manipulación y sin puertos abiertos. MPL-2…
TorusGuard
Autonomous Security Guardrails & Governed Remediation for AI-Built Apps. Tri-Mode Parity (CLI, Chat Slash Commands, Native MCP Server), First-Principles Security Suite, Multi-Moda…
Config Radar
Find MCP server configuration drift across AI coding tools. Read-only, secret-safe, and CI-friendly.
NutritionalTracker
Nutrition label photos become validated macro rows, plus a public REST API and a Claude (MCP) connector whose writes are previewed and saved only on a one-time code. Per-user RLS,…
Vectra
Discover, analyze, and exploit 25,000+ CVEs and 3,600+ GTFOBins payloads instantly via a high-performance offline SQLite FTS5 search engine.
Proworkbench
Local-first AI agent workbench with approvals, tool governance, MCP servers, and a self-check “Doctor”.
Audit Reports
MCP server security & EU AI Act compliance audit reports. Demo: Anthropic filesystem server scored 7/100.
Assurly
Pre-deploy ship gate for AI-generated code — scan Next.js/Supabase/Stripe/Vercel projects before you ship. CLI + MCP server.
Openclaw Setup Guide
Production guide for setting up OpenClaw multi-agent AI platform — Slack bot, n8n MCP, identity stack, security hardening. Based on real law firm deployment.
Sentnel
AI tool call guardrails (Claude hook interceptor)
Story Continuity Guard
Local-first security and continuity auditing for Codex skills, AI-agent configs, MCP projects, and story workflows.
Ao Lens
Agent-native semantic analysis engine for AO/Lua development
Burndrop
One-time, end-to-end encrypted secret exchange between humans and AI agents through a zero-knowledge relay
Scopelens
Your agent needs to read code. Why can it write? Evidence-aware GitHub permission reviews and static MCP configuration checks.
K8s Sec Agent
Kubernetes security audit agent - declarative kagent agent with MCP tools and privacy-preserving pseudonymization via LLM proxy
Aegis Ssh
Local privacy firewall for AI agents: run SSH commands through public aliases while passwords, private keys, hosts, and usernames stay in an encrypted local vault.
Loxeai MCP Server
compliance infrastructure & safety checks
Claude Artifacts Showcase
Standalone reference repo demonstrating every Claude Code artifact type (nested CLAUDE.md rules, sub-agents, skills, hooks, MCP, permissions) against a small real demo app
Cas MCP Connector
Standalone MCP server exposing CAS Engagement Manager tools to third-party AI clients (e.g. Claude, Copilot) with its own OAuth/CIAM login. EM-only; reuses CAS-MCP auth + audit mi…
AgentCommunicationMCP
Authenticated LAN coordination layer for server, dev, and desktop agents
Intervention
Public SDK & MCP clients for Intervention — Robinhood Chain security scanner. Thin hosted clients; no engine or rules.
Uds MCP Power
Kiro Power para integração com o MCP Server da UDS Tecnologia. Uso interno — requer autenticação OAuth 2.1 e credenciais válidas da UDS.
Supply Guard
Offline supply chain security scanner. Detects malicious packages, typosquatting, compromised dependencies, and unsafe CI configurations across npm, pip, Cargo, NuGet, and Maven.…
Metasploit Safe
An MCP server providing a safe environment for LLM-directed pentesting with metasploit
FireMan
MCP Server for Firewall Management via Natural Language Processing (NLP)
PerShiaA Osint
🔌 A curated list of OSINT MCP servers. Pull requests are welcomed!
Oauth Convex Template
MCP server template with Convex OAuth Provider authentication, built with mcp-use