- Conduid
- Marketplace
- #ai-security
MCP servers tagged ai-security
796 live MCP servers tagged "ai-security", ranked by trust score. Tags come from package metadata and repository topics, so this list covers servers across every category that work with ai-security.
Sandboxaq
SandboxAQ — independent third-party profile of a public API surface, by API Evangelist. SandboxAQ (SB Technology, Inc.) builds Large Quantitative Models (LQMs) — AI systems that f…
AI Integration Health Check Demo
Demo repo for an AI/API integration health-check freelance service: IDOR/SQLi/secret-logging fixes side by side (broken vs main), zero-dependency idempotency example, audit report…
Bounded Local AI Demo
OS-enforced isolation demo for bounded local AI: an agent reaches a private vault only through the severino-vault-mcp sensitivity gate, with no filesystem bypass.
SkillWatch
Independent, local-only watcher for the AI-skill supply chain: flags bait-and-switch changes in the pages skills and MCP tools reference. Sends nothing anywhere. Python CLI.
Policies
78 Cedar policies and 369 rules governing AI coding agents. Every rule traces to a real incident, published CVE, or compliance framework requirement (SOC 2, NIST, ISO 27001, E…
Trifecta Guard
Runtime security middleware that blocks lethal prompt-injection capability chains in AI agents.
Scrim
Claude Code plugin that keeps secrets and PII out of the model's context window by reversibly tokenizing them at the tool boundary — the agent works with masked content, real valu…
Pnx MCP Audit
Security audit CLI for Model Context Protocol (MCP) servers. Zero deps, offline, cross-platform.
Bert Bouncer
On-device prompt-injection firewall for Claude Code. Hybrid DeBERTa + masked-LM detection with span localization, content sanitization, and a reproducible red-team evaluation. No…
Axguard
Adversarial security testing for AI agents — MCP, A2A, x402/L402, and live tool-use. Tests as YAML, evidence as JSON.
AI Threats
AI-related threat intelligence pipeline with KEV/EPSS enrichment, MCP server, and Claude-powered classification
Magneto
Magneto is a non-LLM adversarial citation gate whose job is to prevent hallucinations by fact-checking an agent in real-time. Currently for Kiro. EXPERIMENTAL.
AI Agent Security Control Plane
Defense-in-depth security control plane for autonomous AI agents using MCP, OPA/Rego, human approval, adaptive risk, detection, and automated containment.
Audit Truth
Can your agent's logs prove what it did? A review skill that maps AI agent / MCP logging to NIST AU, ISO 27001, SOC 2 and OWASP Agentic Top 10 — with code-level recognisers for ev…
Two Stage Sanitization Architecture
Two-stage security architecture to mitigate indirect prompt injection attacks in rich content via privilege separation
Agent Canary
Tripwire detection for autonomous AI agents: file honeypots, MCP tool traps, API decoys, forensic alerts.
Model Trust Gate
A fail-fast, layered decision gate for deciding whether to trust an AI model for a specific use. A methodology that composes existing standards (NIST, ISO 42001, CSA AICM, OWASP,…
Homebrew Guard
Homebrew tap for HOL Guard — local-first security for AI coding agents
Moorai
MoorAI — open-source, on-device guardrails for AI coding agents (community edition, MIT)
Evidence Validator
Validate what an MCP server declares against what it actually does. Declared-vs-observed checks with a tamper-evident SHA-256 evidence ledger.
Vaultsaas
Self-hosted MCP credential gate for AI agents — short-lived leases, human approval, one-command revoke, tamper-evident audit. Pure Apache-2.0, no SaaS.
Objauthz Lab
Vulnerable-by-design MCP server for learning object-level / cross-tenant authorization (BOLA/IDOR) bugs, plus Semgrep rules that find the same shapes in JavaScript/TypeScript, Pyt…
Threat Detection Lab
Agent exposure review ("what changes if I add this tool to my agent?"), a deterministic detection-boundary harness, and a CTI pipeline. Public data only; every figure measured.
Endpointsweep
Find every MCP server and AI agent on your endpoint fleet. Dependency-free collectors for macOS, Linux and Windows run under EDR/MDM, and a central analyzer audits them against a…
Drift Check
Zero-execution MCP security preflight + GitHub Action. Detect mutable package references before AI agents run them. Try any public repo in the browser.
Agenthive
Multi-agent attack simulation framework for AI systems. 8 attack categories, simulation engine, CLI, SARIF/JSON/HTML reporting, mcp-taxonomy integration.
Arclasp
Runtime governance for AI-agent workflows with cumulative controls and human approval.
Damn Vulnerable Agent Asset Corpus
Damn Vulnerable Agent Asset Corpus: benchmark fixtures for agent-asset scanners and AAC release assurance.
Proofpacket
Privacy-safe evidence packets for AI agent runs
Dvarapala
द्वारपाल — gatekeeper between your LLM and third-party MCP servers. Reads every JSON-RPC message, denies what fails policy, redacts what leaks, audits the rest.
Gateway Production Patterns
Production patterns for secure multi-tenant MCP gateways: Zero-Trust, federation, HITL, sandboxing
Adversa
LLM red-team harness — OWASP LLM Top 10 + MITRE ATLAS attack packs
Security Analysis Multi Agent
Multi-agent MCP server security scanner built with LangGraph — detects prompt injection, SSRF, and risky file/command access.
Hades Blackwatch
Hades Blackwatch is an advanced AI security and code-review skill for auditing LLM, agentic, MCP, and full-stack applications using OWASP LLM/Agentic Top 10, AIVSS, MITRE ATLAS, N…
Trust Scoreboard
Open-source MCP security dashboard and trust scoreboard for Model Context Protocol servers, AI agents, tools, permissions, identity, provenance and risk.
Prompt Injection As An Architectural Primitive
Paper, harness, and raw data: why detection fails against semantic poisoning in agentic LLM pipelines.
Tessyr
Policy and proof layer for consequential AI agent actions.
Agentic Redteam Harness
A/B red-team harness for agentic AI: 34 OWASP-LLM / MITRE-ATLAS attacks fired at a multi-agent app with and without a control plane, plus a live malicious-MCP-server demo. Determi…
Agent Audit Integrity
Two records of one agent run: the agent's own transcript vs a witness proxy's hash-chained log. Shows why a transcript monitor cannot catch a spoofed tool call.
Http Bait
An HTTP honeypot built to measure exploitation rather than discovery: attributable honeytokens, a shared detector table, and a reproducible offline analyzer.
Eczid Agent Trust
Official ECZ-ID Agent Trust product and documentation hub. Local-first agent inventory, authority and change inspection for VS Code.
Whaleguard Redlab
Local-first, scope-guarded AI red-team lab for authorized LLM, Agent and MCP security evaluation.
Llmsafe
Static security scanner for Python AI agents, LLM apps, and MCP servers.
Hallumark
LLM hallucination & grounding auditor for RAG systems
Splunk MCP Guard
Policy-enforcing proxy in front of any Splunk MCP server
AI Security Skill
A prompt-based security audit for AI systems. Copy it, paste it into any AI assistant with codebase access, and get a structured vulnerability report in minutes.
Security Toolkit
13 atomic MCP tools for AppSec and AI Security: recon, MCP audit, prompt-injection audit, OWASP LLM Top 10
Grade Neq Gate
GRADE ≠ GATE — MCP inventory grade is not a runtime gate. Synthetic demo for sentinelagent-guard.
Agent Decoy Policies
Rust and WebAssembly cyber-deception policies for AI agent and MCP traffic on MuleSoft Flex/Omni Gateway: honeytoken detection, decoy tool enforcement, breadcrumb controls, and co…
Cutout
Offensive framework for authorized security testing of agentic AI systems — recon, exploit, persist, and pivot across MCP servers and agent chains.