- Conduid
- Marketplace
- #agent-security
MCP servers tagged agent-security
307 live MCP servers tagged "agent-security", ranked by trust score. Tags come from package metadata and repository topics, so this list covers servers across every category that work with agent-security.
Headroom
More human oversight can make an AI agent less safe. Headroom is a human-in-the-loop firewall for coding agents that measures when to trust the human: oversight as resource alloca…
Nono
agent runtime security - zero trust, zero setup, zero latency agent sandbox
Gateway
A plugin-based gateway that orchestrates other MCPs and allows developers to build upon it enterprise-grade agents.
Cupcake
A native policy enforcement layer for AI coding agents. Built on OPA/Rego.
Agent Security Scanner MCP
Security scanner MCP server for AI coding agents. Prompt injection firewall, package hallucination detection (4.3M+ packages), 1000+ vulnerability rules with AST & taint analysis,…
Compliant LLM
Build Secure and Compliant AI agents and MCP Servers. YC W23
Pic Standard
Open standard for Provenance & Intent Contracts (PIC) in AI agents. Verify intent, provenance, and evidence before high-impact tool calls.
Nia
Nia is a context-augmentation layer for agents, primarily designed for coding agents. It provides them with an up-to-date knowledge base and improves their performance by 27%.
Honeymcp
A Deception Security Layer for MCP Servers. It injects "ghost tools" (fake security-sensitive tools) that act as honeypots.
Agentic Security
Agentic LLM Vulnerability Scanner / AI red teaming kit 🧪
Scanner
Advanced Shodan-based scanner for discovering, verifying, and enumerating Model Context Protocol (MCP) servers and AI infrastructure tools over HTTP & SSE.
Mcptrust
Runtime security proxy for MCP: lockfile enforcement, drift detection, artifact pinning, Sigstore/Ed25519 signing, CEL policy, OpenTelemetry tracing. Works with Claude Desktop, La…
Arcjet Js
Runtime security for AI apps and agents: prompt injection detection, tool-call authorization, sensitive-data redaction, bot protection, and rate limiting. Drop it into your JS/TS…
Cap
What can this MCP server actually do — and has it changed since you trusted it? Inspect its declared capabilities, seal them in a lock file, and get told when a later version can…
Agentseal
Security toolkit for AI agents. Scan your machine for dangerous skills and MCP configs, monitor for supply chain attacks, test prompt injection resistance, and audit live MCP serv…
Doberman Core
Your AI's guard dog. Doberman sits at runtime, gating every input, output and tool call to stop unsafe or unintended actions before they execute.
Secure Claude Code
Security guardrails for Claude Code, MCP tools, and Claude cowork workflows. Local-first modular YARA-style guard packs for secrets, exfiltration, prompt injection, MCP abuse, and…
Sponsio
Deterministic safety solutions for probabilistic AI agents
Adrian
Runtime security monitoring and control for AI agents. Catches malicious tool use, prompt injection, and policy drift in real time, before the agent acts.
Prismor
Runtime security for Agents. Blocks dangerous commands, prevent secret leaks, stop prompt injection, gate risky package installs and visibility and control over tool calls.
Permit0
Stop AI agents from doing things they shouldn't. The action authorization layer — pre-execution, deterministic, policies included. Drop in. Day one.
Vigils
A local control plane for AI agents — see what they do, approve what matters, keep secrets out. Rust + Tauri + Chrome MV3.
Penetration Testing
The ultimate OWASP MCP Top 10 security checklist and pentesting framework for Model Context Protocol (MCP), AI agents, and LLM-powered systems.
nickpending/mcp-recon
Tellix is a conversational recon interface powered by httpx and LLMs. Just ask.
Rampart
Open-source firewall for AI agents. Policy engine that audits and controls what OpenClaw, Claude Code, Cursor, Codex, and any AI tool can do on your machine.
Audit Tool
🛡️ Security audit CLI for Model Context Protocol (MCP) servers — scan AI agent configs for tool poisoning, rug pulls, hardcoded secrets, command injection & supply-chain risks. Pu…
AgentScan
Security scanner for AI-agent configs: MCP servers, CLAUDE.md, settings, hooks. Zero-dependency static analysis.
Helm AI Kernel
Fail-closed execution firewall for AI agents: quarantine MCP tools, proxy OpenAI-compatible requests, emit signed receipts, and verify EvidencePacks offline.
Clawseccheck
🦞 Local, read-only security scanner for OpenClaw. Finds config, prompt-injection and supply-chain risks — A–F grade.
Multi Agent Workflow Lab
Testing and observability for multi-agent delegation, MCP tools, permissions, sandboxed actions, prompts, and workflow replay.
Guardana
Open-source AI security verification — model artifacts, live endpoints, MCP servers and recorded agent traces. One rule engine for your laptop, CI and production, mapped to OWASP/…
Awesome Agent Skills Security
🛡️ A curated list of resources on agent skills security: attacks, defenses, frameworks, and benchmarks for securing AI agent tool use and skill ecosystems
Agent Identity Management
The IAM layer for AI agents: cryptographic identity, capability authorization, and audit trails for non-human identities. Open source.
Awesome Loop Engineering
🔁 Build reliable recurring AI-agent systems: 1001 resources, 22 operational patterns, 22 loop contracts, 8 runtime starters, an interactive atlas, and a structured dataset.
Awesome AI Agent Attacks
A curated timeline of real AI agent security incidents, breaches, and vulnerabilities (2024-2026). Every entry sourced and dated.
Opena2a CLI
Unified CLI for the OpenA2A security platform
Control
Decide which MCP tool calls your AI agents can run: a local gateway with signed policies, one-time approvals and an evidence trail. Experimental alpha. Open source, Go.
Reap
reconnaissance for agent attack surfaces
SafeAI
Static analysis and attack-surface scanner for AI agents — SAST for prompts, tools, MCP servers, and agent workflows. Detects capabilities, prompt risks, tool permissions, and gov…
Little Canary
Detects prompt injection by its effect on a sacrificial canary model, not just pattern matching: untrusted input hits a powerless model first, a behavioral check reads the residue…
Ave
AVE - Agentic Vulnerability Enumeration. The open behavioral classification standard for agentic AI components.
Tap Oss
Credential isolation for AI agents — stop leaking secrets to your agents. TAP is a credential proxy: agents never see secret values; optional human approval on sensitive calls. By…
Stroq
Local action firewall for AI coding agents: scans what the agent reads, taints the session, blocks dangerous follow-up actions
Soup Wall
Soup Wall: a local firewall for what an AI agent does - tool calls, tool results, MCP handshakes, subagents. Deterministic, shadow-first, no account, no network.
OpenTrustBench
Trust & security scanner for AI agents and MCP servers — OWASP-mapped findings, Trust Cards (A–F grades), SARIF + CI gate. Free CLI, zero telemetry.
Squidbrake
Brakes for your AI agents: every tool call is checked against your rules, held for human approval when risky, and recorded in a tamper-evident audit trail. Works with Claude Code…
Memnox
Your agents can already do the work. Memnox makes it safe to let them do it without you. See what Claude Code, Codex and Cursor can actually do on your machine, and put the danger…
Agent Kernel
Capability-based authorization and policy enforcement for agents using large MCP and A2A tool ecosystems.
Aegis Memory
Secure context engineering for AI agents. Content security · integrity verification · trust hierarchy · ACE patterns. Self-hosted, Apache 2.0.
Bluerock
Runtime visibility for Python MCP servers. Captures tool calls, session lifecycle, module imports (SHA-256), and subprocess execution as structured NDJSON. No code changes. Apache…