- 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.
Jakk
Black-box security scanner for MCP servers — deterministic single-call probes, no LLM. 13 probes across 7 surfaces.
Mcpnuke
MCP red teaming & security scanner — enumerate, probe, and exploit Model Context Protocol servers
Attestral
Open-source security scanner for MCP servers and AI agents: finds prompt injection, tool poisoning, and excessive agency, and models the cloud your agents can reach. pip install a…
Pin
Tool-integrity pinning for MCP. Pin what your agent approved; block it when it changes.
Bastyn Scan
Static analysis for AI and agent code: Python, TypeScript, JavaScript, MCP manifests, and dependency CVEs.
AistyMCP
Secure MCP setup, where users can define the permission set instead of allowing the tool to access and execute anything.
Copyleftdev
Systems-level software engineer building security tools, developer infrastructure, and AI-native systems in Rust, Go, and Zig. 560+ open source repositories.
Registry Audit
Read-only reconnaissance CLI that scans public MCP registries for rug-pull and lookalike supply-chain attacks.
Kong MCP Oauth2
MCP OAuth2 plugin secures Model Context Protocol (MCP) traffic on AI Gateway using OAuth 2.0 specification for MCP servers
Navra
Secure MCP gateway for AI agents — deny-wins ACLs, IFC, in-process ML safety, 138 Kani proofs
Coven Scout
Fast, sandboxed Rust MCP server for filesystem and web operations in the OpenCoven ecosystem.
Seatbelt
Seatbelt for MCP tools: local policy checks, audit logs, and a dashboard for safer AI tool use.
Ops Pilot
Production-grade multi-agent AI DevOps system for SRE incident response, where a central orchestrator coordinates 12 specialist agents to classify incidents, traverse service depe…
Orivra
Verify the connection, not just the proof. Developer assurance for Flare Web2Json: persisted Coston2 evidence, URL-invariant checks, source-bound Solidity, reproducible integratio…
Drift Monitor
Continuous MCP Registry Drift Monitor with content-binding revalidation — closes the gap identified in arXiv:2608.00997
Mcpseal
Local-first MCP config risk linter for agent server definitions
Secnews
v0.8.1: 面向 AI + 安全从业者的单人本地工作站 · Sentinel Terminal 三层工作流 (Data/Judge/Action) · llm-wiki-2.0 wiki-first 知识库 · CodeGarden 项目全生命周期 · 七 gate 开闸 + 运行时弹性层 + graceful shutdown · MCP 开放 19…
Xshell Agent Bridge
面向 Codex、Claude Code、Cursor、Kimi 等 AI Agent 的本地 Xshell MCP 安全桥接：读取终端、合并步骤确认命令、安全上传/下载文件，密码由用户亲自输入，并硬性拦截删除、格式化、数据库清空等危险操作。适用于服务器部署、巡检、排障和离线运维。
Cveasy Forge
The CVEasy open lab — runnable security harnesses, red-team probes, and experiments. Good-faith open source from CVEasy AI.
AI Workspace Showcase
Bilingual AI prompts library, MCP registry & developer workbench — Public showcase with type-safe mock layer and C4 architecture.
Detect
Open-source MCP abuse-detection lab with reproducible rules, corpora, and coverage limits
Hachiman Agent
Hachiman Agent — autonomous security layer for AI agents and MCP. Scan before deployment, authorize before access, monitor during execution, contain when compromised, report every…
Memwall
Antivirus for AI agent memory - scanner + MCP firewall for memory poisoning (OWASP ASI06)
LLM Code Security Review MCP
MCP server for running source code security reviews with an LLM
Mcpcanary
Local-first MCP trust scanner and semantic drift canary for AI agent tool configs
Vestibule
Vestibule - A kernel-isolated code-execution sandbox for AI agents, as an MCP server. Run untrusted/questionable agent code safely — local, free, no cloud.
Safe Commander MCP
A secure MCP server for executing whitelisted development commands with comprehensive security controls.
Aphelion Agent Security Framework
A lightweight, modular security framework for AI/ML models, agents, tools, and data, targeting Google ADK, Anthropic MCP, and extensible protocols that emphasizes ease of use, zer…
Developer Assistant
MCP server with AI-powered code intelligence, OAuth 2.1 security, behavioral anomaly detection, and semantic code search.
OAuth 2.1 MCP Gateway
Self-hosted OAuth 2.1 authorization server and reverse proxy for MCP servers — PKCE-mandatory flows, audience-scoped JWTs, per-tenant access control.
Neo4j Yass MCP
Production-ready, security-enhanced MCP server for Neo4j with LLM integration. Transform natural language into graph insights with enterprise-grade security.
Dotnet MCP Identityserver
ASP.NET Core MCP server with Identity Server JWT authentication, featuring weather tools and Claude AI integration
OmniScrape
Secure hybrid web extraction toolkit: deterministic parsing, SSRF-hardened async fetching, optional Playwright/OpenAI, FastAPI, CLI, MCP, and a polished web console.
Web Vuln Scanner MCP
OWASP Top 10 vulnerability scanner MCP — SQL injection, XSS, CSRF, and authentication flaw detection for web applications.
Sec Certipy MCP
MCP server for Certipy - AD CS attack tool
Toolrampart
A Python framework for exposing functions as safe AI-agent and MCP-compatible tools.
Vivarium MCP
Secure MCP server exposing headless, out-of-process Ghidra (12.1.2) to LLM clients: read + consent-gated write reverse-engineering tools, with hardened disposable worker isolation.
Policy Forge
Least-privilege MCP tool policy generator, validator, risk scorer, diff reporter, and CI gate.
Appwrite Security MCP
MCP server for Appwrite security audits inside Claude Code, Cursor, Cline.
Secops
Security operations as conversation. An MCP server connecting 13 security platforms (Wiz, Kodem, GitHub, Okta, SentinelOne, Apono, Twingate, Pluto, Panorays, Abnormal, Slack, Mond…
Registry Risk Scanner
Static security scanner for MCP server.json registry manifests. Flags supply-chain, transport, credential, and data-egress risks before you install a server.
Agentmoat
A security layer for AI agents: detects prompt injection, firewalls dangerous tool calls, scores inter-agent trust, and keeps a tamper-evident audit log. Works with the Anthropic…
Aps MCP Security
APS-MCP: The first formal security standard for MCP (Model Context Protocol) tool integrations
Llmesh
Security-first local LLM swarm over MCP with signed peer discovery, fail-closed validation, audit trails, and Docker-based PoC nodes.
Vaultwarden Secrets
Secure secrets management with Vaultwarden/Bitwarden CLI, encrypted caching, and macOS Keychain
Workspace Admin Auditor MCP
MCP server that audits Google Workspace roles, groups, OAuth grants, and user hygiene.
Safe MCP Config
Zero-dependency CLI that catches risky MCP config patterns before they leak into docs, issues, repos, or shared setups.
GhostInTheShell MCP
🔒 A sandboxed, read-only MCP server that safely exposes system health, Docker diagnostics, and log intelligence to AI agents like Claude — with strict path whitelisting, context c…
Zfuzz MCP
Security copilot for AI coding agents. 10 MCP tools — SAST, SCA, secrets, MCP/skill scanning — for Claude, Cursor & co. Rust-native, local, $0, Apache-2.0.
Kennelbox
A kennel for your AI agents — firejail-sandboxed MCP workspace with default-deny command and file policies.