- 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.
io.github.New1Direction/trust-oracle
Independent A-F trust grade for any MCP server, watched for drift. Free, never for sale.
Outlook SNDS
Outlook.com SNDS IP Data and IP Status reports via the OAuth-secured REST API.
Retro Diffusion Pixel Art
Generate authentic pixel art - sprites, animations, and tilesets - from any MCP client
Bugwarden
Security-guarded MCP server for Bugzilla, written in Rust
Sovereign Observer MCP
Scan Terraform for security misconfigurations while your AI assistant writes it. Local-first MCP server for Claude Code, Cursor, VS Code and Windsurf.
Oauthlint
Catch the OAuth, OIDC, JWT & MCP security bugs AI coding assistants ship on repeat, across ten languages (JavaScript, Python, Go, C#, and more). A free, low-false-positive linter…
Recon
A comprehensive Model Context Protocol (MCP) server for web security reconnaissance and analysis.
MCP-native URL security scanner that protects AI agent workflows.
Analyzes threats and verifies URLs align with the agent's intended goal.
goklab/guardvibe
commit hook, and CVE version detection. Zero config, runs locally.
Lionguard
Cathedral-Grade Security for AI Agents. Attack vectors updated daily. Local-first, zero API cost. MIT licensed.
MemAuthority
Git-backed long-term memory authority for AI agents via MCP.
Coldforge
Render personalized cold-outreach sequences from Markdown templates + a contacts CSV, with spam-score linting and per-send dry-run preview.
Marksentry
Secure, local-first document-to-Markdown conversion. Zero-trust input sanitization, multi-column PDF layout, LaTeX math, PII masking. No cloud dependencies.
Polar MCP Server
A Model Context Protocol (MCP) server that provides AI assistants with access to the Polar AccessLink API v3
Multi Ssh MCP
Multi-Server SSH MCP Server - Connect any LLM to multiple SSH servers with secure credential management
CyberNewsMCP
MCP server to aggregate and analyze cyber security news
Drata MCP
MCP server for Drata compliance automation - SOC2 Type II task management with Claude
KaliMCP
MCP server exposing a curated subset of Kali Linux security tools to an AI agent.
Pyntra
AI-native security testing platform - multi-agent orchestration, for authorized pentesting.
Open Legal Compliance MCP
Model Context Protocol server for legal compliance analysis using free/open government APIs
io.github.bkalafat/diffpilot
MCP server for PR code review, commit messages, changelogs, and secret detection.
Ghas MCP Server
MCP Server for GitHub Advanced Security
Zap MCP Server
Production-grade OWASP ZAP MCP server for authorized penetration testing and bug-bounty workflows (67 curated tools, authenticated scanning, target authorization policy).
My First MCP
first mcp server
PCI DSS v4.0.1 Compliance Checker
PCI DSS v4.0.1 compliance scanner for Go payment services, delivered as an MCP server
Wavix
Hosted MCP server for the Wavix telecom platform: SMS, voice, 2FA, SIP, numbers, 10DLC, CDRs.
Hercules
Hercules is a professional-grade, autonomous penetration testing and Capture The Flag (CTF) solving platform. It orchestrates intelligent AI agents using CrewAI, connects them to…
McpNet
A high-performance, enterprise-ready Model Context Protocol (MCP) gateway for .NET 8. Aggregate any number of upstream MCP servers behind a single authenticated endpoint - wit…
Beforeship
Open-source launch gate for vibe-coded apps: CLI + MCP pre-deploy checks for auth, payments, secrets, Supabase, and production readiness.
Code Review Agent MCP
AI code review agent MCP server. Reviews code like a kernel maintainer: blunt, technical, no sugarcoating. Detects bugs + OWASP Top 10 security vulnerabilities. 4 harshness levels…
Claude Worker Proxy
Convert Gemini and OpenAI APIs into Claude-like format and serve them via Cloudflare Workers. 🚀 Zero-config, streaming ready, tool calls, and one-click deployment.
OneKey MCP Router
OneKey MCP Router Helps you with One Access Key to Access Various Commercial MCPs with Free Tier or Discounted API prices
Sliver MCP
Python MCP server for Sliver C2 — exec, armory (aliases + BOFs via coff-loader), listeners, implants, identity, recon, intel. Complements the official fs-only MCP.
Browser Integration MCP
Control a dedicated Chrome, Edge, or Vivaldi browser profile from Claude Desktop using this secure MCP server with Chrome DevTools Protocol support.
Oauth Demo
With Pocket ID, you can protect your MCP server with OAuth 2.1 and OpenID Connect. This demo shows how quickly OAuth can be added to an MCP server with Pocket ID.
DB MCP GATEWAY
Self-hosted MCP gateway: AI agents get audited, SSO-gated, read-only database access without ever holding a DB credential.
Drupal Bridge MCP
MCP Server for Drupal integration with OAuth authentication and zero configuration
Hacking Buddy MCP
Hacking Buddy MCP is a proof-of-concept MCP Server showing how AI can be leveraged in security operations/engagements.
Nooscope
A local sidecar MCP to allow my local knowledge vault to be persistent memory for AI
Claude On A Leash
Deterministic security guardrails for Claude Code. Six hooks that hard-block RCE, credential exfiltration, SSRF, and prompt injection before they execute. Plus an MCP server for e…
Tsk
tsk is a local MCP server that sits between your AI agent and external APIs. It holds your credentials, enforces per-tool call rules, scrubs sensitive data from API responses befo…
Aibuster
Reconnaissance for AI agents, MCP servers and AI/ML infrastructure for offensive security.
Stepsecurity MCP
Model Context Protocol (MCP) server for the StepSecurity platform
Keyring Injector
Session-scoped MCP credential security - keys auto-injected at startup, auto-removed at exit, zero config file exposure
Exodus Ia Firewall
🛡️ Local privacy firewall for AI coding agents — masks API keys & personal data before they reach the cloud, then restores them transparently.
Security Agent Skills
Security-testing methodology as portable, tool-agnostic agent skills for Claude Code and any agent runtime: white-box bug hunting, AI-agent and LLM red-teaming, supply-chain risk,…
TrustVector
Independent, evidence-based trust evaluations for 100+ AI models, agents, and tools.
Guarded Computer Use MCP
Windows computer-use MCP server (26 tools) with a human-in-the-loop approval gate: physical-input-only dialogs, signed guard switches, deny/launch lists, hash-chained audit log. 7…
Snare
Self-contained HTTPS intercepting proxy — Repeater, Intruder, Comparer, match/replace, HAR — with a web UI, a CLI, and an MCP server so an AI agent can drive it.
The Ideal Harness
Agent harness / control-plane around a stateless LLM: deterministic policy floor on PreToolUse/PostToolUse hooks, secret redaction, injection fencing, tool-result compression, cod…