- 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.
Find Evil
AI-driven autonomous incident response agent using SIFT Workstation via MCP — FIND EVIL! Hackathon by SANS Institute
Sigstore Cosign MCP
🔌 Exposes Sigstore cosign + Rekor transparency log verification.
Project Sentinel
npm audit for AI agents — scan, certify, and enforce trust for MCP servers. Security scanner, trust certificates, YAML-configured gateway.
Sec Feroxbuster MCP
MCP server for feroxbuster - Fast content discovery
Github Insight MCP
Stop opening 12 tabs to evaluate a library. GitHub repos + npm/PyPI packages + security advisories in one MCP tool call. Zero API keys required.
Mcpshield Runtime
Open-source Rust runtime sandbox for MCP servers — capability allowlists, outbound proxy filtering, DLP, HMAC policy snapshots, OTel GenAI telemetry. NSA May-2026 aligned.
Aiops MCP
A self-contained, security-first unified AIOps MCP
Stage0 Authorization
MCP server demonstrating server-side authorization with Stage0 runtime policy validation
Sec Gobuster MCP
MCP server for gobuster - Directory brute-forcer
Sec Ldapdomaindump MCP
MCP server for ldapdomaindump - Active Directory LDAP enumeration for penetration testing
Darvoza
MCP governance gateway — deny-by-default per-role tool policy and a 100%-coverage audit trail in front of any MCP server. Azure DevOps ships as the default profile and the demonst…
Detection Lab
Detection-engineering for MCP: working Sigma rules for the OWASP MCP Top 10 + isolated home-lab + zero-dependency validator (git clone && python3 validate.py).
Security Evidence Redactor
Dependency-free JSON findings summary that emits severity counts without copying finding details.
Bathy
Agent-native network discovery. Typed MCP tools, evidence-backed findings, deny-by-default scope enforcement.
Anvilogic
Anvilogic — independent third-party profile of a public API surface, by API Evangelist. Anvilogic is an Agentic SecOps platform founded in 2019 by former SOC practitioners. It run…
Best MCP Servers
MCP servers ranked by measured uptime and real installs — not stars. Daily change log, weekly ecosystem reports, open data.
Bedrock Security MCP
ARCHIVED: development moved to github.com/AUAggy/agent-sec-scanners (packages/bedrock). npm package unchanged. MCP server + CLI auditing AWS Bedrock security posture: IAM, logging…
Subject Broker
An experimental MCP context broker: one process per subject, default-deny policy, fail-closed audit — with field-tested evidence on agent delegation.
Windsurf Deepwork
Evidence-gated MCP, hooks, skills, and workflows for deliberate coding in Windsurf.
Tlad Semgrep
Semgrep rules to detect Transport-Layer Auth Divergence (TLAD) in MCP servers — auth applied to some transports but not others.
Toolprint Watch
Daily observation of public MCP servers. The git history of baseline.json is the dataset.
Marco Polo
Marco Polo — independent third-party profile of a public API surface, by API Evangelist. MarcoPolo is an MCP-first enterprise AI data platform operated by Immersa - "Scale AI acro…
Toolgraph
Graph-native MCP tool registry: explainable, advisory governance and impact analysis over a tool/policy graph
Cymulate MCP Tools
Community MCP for Cymulate — 100% API coverage (337 endpoints) via 106 tools. BAS, Exposure Validation, ASM, Purple Team. STDIO + HTTP transport.
Warder
A policy gate for MCP tool calls. Blocks destructive AI agent actions before they run — as the subprocess your AI client launches, where network gateways can't see.
Package Verify MCP
MCP server that verifies an npm package name is real before an agent installs it — catches hallucinated 'slopsquat' names and typosquats. Public registry only.
Audit Scanner
Read-only AST security scanner for Python Model Context Protocol servers before connecting them to AI clients.
Exploit Validator
Proves whether AI agent (MCP) tool configurations are actually exploitable - not just risky-looking. Existing scanners infer risk from manifests; this one validates it in a sealed…
Secure Files Organizer MCP
إدارة وتنظيم آمن للملفات عبر خادم MCP مع تأكيد الحذف البشري | A secure local MCP server for file triage, organization, and human-in-the-loop safe deletions.
Bluerock Security
Bluerock Security — independent third-party profile of a public API surface, by API Evangelist. BlueRock Security is a runtime security, observability, and governance platform for…
Smcp
Semantic ontology bindings for Model Context Protocol (MCP)
Code Security MCP
Security MCP server for AI agents — native per-language analysis: Kotlin (detekt), Java (SpotBugs), Python (Bandit), C# (Roslyn); diff review; secure patterns
Codex MCP Doctor
'npm doctor' for MCP. Diagnose broken servers, Cyrillic homoglyph attacks, and silent rug-pulls - zero deps, 287 tests. Built in Codex with GPT-5.6.
Proxmox Safe MCP
Constrained Proxmox MCP server with exact-confirmation mutations
Safemcp Gateway
MCP security gateway with zero dependencies - blocks prompt injection, path traversal and SSRF attacks on AI agents.
Zastava
MCP gateway in Rust: argument-level policies ("github, but only repo X"), audit log, and rules learned from observed behaviour.
Natoma
Natoma — independent third-party profile of a public API surface, by API Evangelist. Natoma is an enterprise Model Context Protocol (MCP) platform that lets organizations securely…
Readonly SQL Guard
A provably read-only SQL guard for AI agents — drop it into any MCP server or database tool. Checks what a statement calls, not just its shape; measured against a public 28-attack…
Turnstile
Scan any MCP server: a token-cost + metadata-safety report card at the tools/list boundary. Deterministic, i18n-honest concealment detection. Python + TypeScript.
Prometheus Safe MCP
Constrained Prometheus MCP server for bounded, audited observability queries
Ccs Integrations
Framework-native adapters for CCS (Correctover Conformance Shape) cryptographically signed runtime receipts — Ed25519 + JCS signed audit evidence for AI agent tool calls (Pydantic…
Vmette
A hardware-isolated microVM sandbox for running untrusted local AI agents on macOS.
Leanproxy MCP
A "Token Firewall" for MCP - reduce AI token costs by 50-80% while securing your code from secret leaks.
Nyxora
A zero-trust, local-first AI execution framework for autonomous Web3 agents. Features OS-native keyring security, advanced DeFi automation, and Google Workspace integration.
Xche AI App Security Pack
Free security guardrails for apps built with AI coding tools (Claude Code, Cursor, Lovable, Bolt). Drop-in rules + OWASP/LLM/MCP policy + secret-scanning hooks & CI gate.
Pkgseek Skills
One Linux Agent Skill for package errors, CVE/CNNVD, distro migration, ELF/ABI, command portability, and containers, powered by PkgSeek.
Secchecker
Static security scanner and analyser for AI agents, MCP tools, and LLM applications - OWASP LLM Top 10, and infrastructure checks. Zero runtime dependencies.
Agentic Firewall
Agentic Firewall sits between an AI agent or MCP client and an MCP server. It can enforce runtime policies and automatically test the server's tool-use attack surface with 17 OWAS…
Compliance Agent Skills
30 Agent Skills for deterministic USA compliance auditing of AI agents — HIPAA, NIST AI RMF, FERPA, COPPA, PCI-DSS, SOC 2, FedRAMP, CMMC, GLBA, privacy & GDPR. Presidio PHI redact…
SleepyWalker
🛡️ Autonomous SQL injection pipeline — crawls, probes, confirms with AI, exploits with sqlmap, reports in HTML/JSON/SARIF. Built for authorized red teams. One command, full databa…