- 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.
LocalHands
A guarded local MCP server that lets a cloud AI agent operate one real machine - path whitelist, command guard, audit log. 222 tests.
Agent Security Lab
A local, dependency-free lab that reproduces MCP / AI agent attacks and the audit that catches them. Educational and defensive. Runs on python3 alone, offline.
Spendveto
Spend governance for AI agents paying over x402. Payment rails move an agent's money; SpendVeto decides whether it should be allowed to move it — caps, budgets, human approvals an…
Tokenstash
Your agent asks you for a key once. Never again — in any project, in any agent.
Sysadmin
Provider-agnostic MCP server for SSH, Proxmox, and Virtualizor infrastructure
Skillfrisk
Static security scanner for AI agent skills and MCP servers. No LLM, no network, no Docker: millisecond scans with a public zero-false-positive regression corpus
Sentrymcp
A static + runtime security scanner for MCP (Model Context Protocol) servers
Guarded Notes MCP
Safety-gated Apple Notes MCP server and Codex plugin for macOS: local review, exact move plans, one-use authorization, journals, and rollback.
Laravel Agent Kit
Give an AI agent your Eloquent models, not your database. Field allowlists, per-record policy checks and result ceilings, every one of them failing closed.
Mcpxray
Static linter + 0-100 scorecard for MCP servers. OWASP MCP Top-10 rules (MCP101-109), Python + TypeScript static extraction, opt-in runtime tools/list capture, score + SVG badge.
Mcpg Plugin Security Dlp
Data-loss-prevention ToolGate plugin for MCPG (dev.mcpg.tool-gate.dlp) — detects/blocks/redacts secrets + PII in tool arguments and results.
Governed Rag MCP
Fail-closed hybrid RAG over MCP with ACL, grounding, and measurable retrieval.
Restic Defensive MCP
Structurally read-only MCP server for inspecting restic repositories.
Security Showcase Server
A remote MCP server done right: OAuth 2.1 resource server with audience binding, tenant isolation, audit log, rate limiting. 26 tests; CI dogfoods mcp-sec-scan.
Vetmcp
Security scanner for MCP servers — npm audit for the Model Context Protocol
Pulr
Secure file exchange for AI agents — scanned, provenance-stamped files behind expiring capability URLs, with human approval gates and Ed25519-signed receipts. MCP server + JS/Pyth…
Contextlint
Audit what your AI coding assistant loads before you type: token cost, dead weight, and MCP security risk — across Claude Code, Codex, Cursor and Copilot.
Project3 MCP Infra Operator
Autonomous Kubernetes remediation agent via MCP. 5 secured tools, 3-layer security (token auth + namespace sandbox + audit log), dual-transport stdio/HTTP, CrewAI + LangChain agno…
Heron MCP
Free, signed 0-100 trust scores for what an AI agent runs: skills, MCP servers, and the agent itself. Public methodology, wallet-signed (EIP-191).
Vpsobs
Read-only observability MCP server: give an agent eyes on a production host, not hands
Cvdportal MCP
MCP server and agent skills for CVD Portal. Coordinated vulnerability disclosure and EU Cyber Resilience Act compliance for manufacturers.
Redwrench
A security-conscious MCP server exposing Fedora hardware and OS control to AI coding agents
Glama MCP SDK
Glama MCP SDK for Python/FastAPI: secure client + typed API. TLS, timeouts, retries, pooling. Access 5,000+ MCP servers or run as an MCP server. Optimized for www.glama.ai
Thales Dpod MCP Server
A Model Context Protocol (MCP) server for interacting with Thales Data Protection on Demand (DPoD) platform. Manage services, retrieve audit logs and all of the other DPoD feature…
Orbitl MCP
Historical audit findings for Web3 security review, served over MCP
Nimbus MCP
Nimbus - AWS Security Assessment MCP Server | 45 Tools | Multi-Region Scanning | TRA Reports | CIS/NIST/PCI-DSS Compliance
Privacy Shield MCP
7-layer security plugin for Claude Code: real-time hooks (bash, file, web) + 21 MCP tools for privacy, threat detection, and audit
TelsonBase
Open Source Real Time Local-First Gateway for Autonomous Agents | Checks Permissions on Every Action
Wssch
Takes care of you while you code for them 🫰🎇. Planned migration to Rust or C++23 soon.
Vuln Analyzer
Agentic vulnerability analyzer for Claude Code — runs grype via MCP, ranks findings, dispatches reachability / context / remediation sub-agents per top-5 vuln.
Permission Policy Tester
Scan MCP tool descriptions and schemas for risky permission policy signals.
AI Protect
AI-application security assurance pipeline: tier-aware SAST · DAST · AI red-team scanning with a findings dashboard, CVE intel feeds & auto-remediation. For AppSec & platform team…
AntiPrivEsc
Detect privilege escalation and suspicious processes with process monitoring, file tracking, and SQLite logging for security teams
Claude Code Map
Map Claude Code projects with a clear MCP-driven view of files, paths, and structure
Subprocess Env
Compile provenance-aware, auditable environment objects for child processes.
Permitd
Governed tool execution for agent loops: propose -> permit -> approve -> execute -> audit. Fail-closed, zero dependencies.
Risk Inventory
Dependency-free MCP configuration risk inventory CLI and GitHub Action
Agent Skill Aegis
中文 Agent Skill 与 MCP 配置供应链安全扫描器，支持终端、JSON、HTML 与 SARIF 报告。
React Native Security Toolkit
Mobile security toolkit for React Native: runtime root/jailbreak, debugger, hooking and integrity checks on Android and iOS, a static auditor with OWASP MASVS/CWE mappings and SAR…
INTENTRA
Authority provenance layer for agent chains. AI agents can delegate work. Authority cannot.
Actgate
Local IntentLedger + MCP stdio proxy: propose, approve/deny, hash-chained ledger. Optional HMAC seals.
CurocX VPS Terminal
Bounded, safety-focused VPS terminal connector for AI tool workflows.
Kirby Agent Security
SOP for auditing and validating third-party AI agent skills, plugins, and MCP servers prior to installation.
Swarmops SENTINEL AWS
Sentinel — AI Security Officer for Ring (Amazon hackathon). Ring + Bedrock, governed by SwarmOps.
Code Clearance
Evidence-based clearance for AI-generated code.
Mcpguard Go
mcpguard-go: local AI agent security scanner (Go, zero-dep single binary)
Urlscan MCP
MCP server for the urlscan.io API - 14 tools, shaped responses (240-812x smaller), no false-clean verdicts.
Remote MCP Ping Federate
CF Workers MCP Server + PingOne AIC. MCP Server is a RS while PingFederate handles all auth.
Notevault
Local-first Obsidian-style notes with MCP (NoteVault take-home)
Fire Drill
Local-first fire drills for MCP and AI agent security.