# Guardrails and security

Defences for agents and the applications around them: filters for prompts and outputs, policy engines that decide what an agent may do, scanners for MCP servers, red-teaming tools, and the published lists of risks they answer to.

69 tools, in alphabetical order. Nothing is ranked by popularity.

- [Aembit](https://modelmoot.com/tools/aembit.md): A runtime identity and access service for AI agents and other workloads that keeps downstream credentials out of agents. (Aembit; not open source, hosted service)
- [Agent Governance Toolkit](https://modelmoot.com/tools/agent-governance-toolkit.md): A Microsoft toolkit that checks every tool call, message and delegation of an AI agent against policy before it runs. (Microsoft; open source)
- [AgentDojo](https://modelmoot.com/tools/agentdojo.md): A dynamic environment that measures how tool-using agents resist prompt injection attacks, and how well defences work. (ETH Zurich SPY Lab; open source)
- [Agentic Radar](https://modelmoot.com/tools/agentic-radar.md): A command-line scanner that maps the workflow, tools and MCP servers of an agent system and links them to known vulnerabilities. (SPLX (Zscaler); open source)
- [Airia](https://modelmoot.com/tools/airia.md): An enterprise platform for securing and governing models, agents and tools, with an agent builder and an MCP gateway. (Airia; not open source, hosted service)
- [Akto](https://modelmoot.com/tools/akto.md): A security platform that discovers, tests and guards AI agents, MCP servers and LLM applications, with an MCP proxy. (Akto; open source, hosted service)
- [Amazon Bedrock Guardrails](https://modelmoot.com/tools/amazon-bedrock-guardrails.md): An AWS service that filters model inputs and outputs for harmful content, prompt attacks, sensitive data and ungrounded answers. (Amazon Web Services; not open source, hosted service)
- [Arcjet](https://modelmoot.com/tools/arcjet.md): Runtime security for AI apps and agents, covering prompt-injection detection and tool-call authorization. (Arcjet; open source, hosted service)
- [Arthur](https://modelmoot.com/tools/arthur.md): A platform for discovering, monitoring and governing AI agents, with a public engine repository for evaluation and tracing. (Arthur; open source, hosted service)
- [Astrix Security](https://modelmoot.com/tools/astrix.md): A security product for discovering and governing AI agents and non-human identities. (Astrix; not open source, hosted service)
- [Augustus](https://modelmoot.com/tools/augustus.md): A Go command-line framework for testing LLMs for prompt injection, jailbreaks and other adversarial weaknesses. (Praetorian; open source)
- [Azure AI Content Safety Prompt Shields](https://modelmoot.com/tools/azure-prompt-shields.md): A service in Azure AI Content Safety that detects prompt injection and jailbreak attempts in user input and documents. (Microsoft; not open source, hosted service)
- [Cedar](https://modelmoot.com/tools/cedar.md): A policy language and evaluation engine for authorization decisions, with schemas and formal analysis tools. (Amazon Web Services; open source)
- [Cisco AI Defense](https://modelmoot.com/tools/cisco-ai-defense.md): A commercial Cisco product that discovers AI use, red teams models and agents, and enforces guardrails on AI traffic at run time. (Cisco; not open source, hosted service)
- [Cisco MCP Scanner](https://modelmoot.com/tools/cisco-mcp-scanner.md): A scanner from Cisco that checks MCP servers for potential threats and security findings. (Cisco AI Defense; open source)
- [Cybench](https://modelmoot.com/tools/cybench.md): A benchmark of professional-level capture-the-flag cybersecurity tasks for language model agents. (Stanford University researchers; open source)
- [DeepTeam](https://modelmoot.com/tools/deepteam.md): An open-source Python framework for red teaming LLMs and agents against vulnerabilities and attack methods. (Confident AI; open source)
- [Docker MCP Gateway](https://modelmoot.com/tools/docker-mcp-gateway.md): A Docker CLI plugin that runs MCP servers in containers and exposes them to clients through one gateway. (Docker; open source)
- [Enkrypt AI](https://modelmoot.com/tools/enkrypt-ai.md): A commercial platform that red teams AI systems, applies real-time guardrails and monitors AI agents. (Enkrypt AI; not open source, hosted service)
- [F5 AI Guardrails](https://modelmoot.com/tools/f5-ai-guardrails.md): A commercial runtime security product that screens AI models and agents for prompt injection, data leakage and harmful output. (F5; not open source)
- [Fiddler AI](https://modelmoot.com/tools/fiddler.md): An enterprise platform for monitoring, evaluating and governing AI agents and predictive machine learning models. (Fiddler AI; not open source, hosted service)
- [garak](https://modelmoot.com/tools/garak.md): A command-line vulnerability scanner for LLMs that probes models with attacks such as jailbreaks and prompt injection. (NVIDIA; open source)
- [Giskard](https://modelmoot.com/tools/giskard.md): An open-source Python library for evaluating and testing LLM agents, including checks for security and quality issues. (Giskard; open source, hosted service)
- [Granite Guardian](https://modelmoot.com/tools/granite-guardian.md): A family of open IBM models that judge prompts and responses for harm, jailbreaks and hallucinations in RAG and tool calls. (IBM; open source)
- [Gray Swan](https://modelmoot.com/tools/gray-swan.md): A commercial AI security company with automated red teaming, a runtime filter for agents and a public red teaming arena. (Gray Swan AI; not open source, hosted service)
- [Guardrails AI](https://modelmoot.com/tools/guardrails-ai.md): A Python framework that checks and constrains LLM inputs and outputs with validators from a shared hub. (Guardrails AI; open source)
- [Hamming](https://modelmoot.com/tools/hamming.md): A hosted platform for testing, red-teaming and monitoring voice and chat AI agents. (Hamming; not open source, hosted service)
- [HiddenLayer](https://modelmoot.com/tools/hiddenlayer.md): A commercial AI security platform covering discovery of AI assets, model scanning, attack simulation and runtime protection. (HiddenLayer; not open source, hosted service)
- [Invariant Guardrails](https://modelmoot.com/tools/invariant.md): A rule-based guardrailing layer that checks agent traces and tool calls against policies written in a Python-like language. (Invariant Labs (part of Snyk); open source)
- [Lakera](https://modelmoot.com/tools/lakera.md): A commercial service that screens prompts, responses and tool use of AI agents and LLM applications, with AI red teaming. (Lakera (Check Point); not open source, hosted service)
- [Lasso Security](https://modelmoot.com/tools/lasso-security.md): A commercial platform that protects AI agents and applications, with open-source MCP gateway and Claude Code hooks. (Lasso Security; not open source, hosted service)
- [LlamaFirewall](https://modelmoot.com/tools/llamafirewall.md): A Python guardrail framework from Meta that runs layered scanners over the inputs, reasoning and outputs of LLM agents. (Meta; open source)
- [Lunar MCPX](https://modelmoot.com/tools/lunar-mcpx.md): A self-hosted gateway for MCP traffic with governance, logging and access control. (Lunar; open source)
- [MAESTRO](https://modelmoot.com/tools/maestro.md): A threat modelling framework for agentic AI that analyses risks across seven layers of an agent system. (Cloud Security Alliance; not open source)
- [Mindgard](https://modelmoot.com/tools/mindgard.md): A commercial platform that tests AI systems and agents by attacking them as an adversary would. (Mindgard; not open source, hosted service)
- [MITRE ATLAS](https://modelmoot.com/tools/mitre-atlas.md): A knowledge base of adversary tactics, techniques and case studies for attacks on AI-enabled systems. (MITRE; open source)
- [Model Armor](https://modelmoot.com/tools/google-model-armor.md): A Google Cloud service that screens prompts and responses for prompt injection, jailbreaks, sensitive data and malicious links. (Google Cloud; not open source, hosted service)
- [ModelScan](https://modelmoot.com/tools/modelscan.md): A command-line scanner that checks saved machine learning model files for unsafe serialised code. (Protect AI; open source)
- [NeMo Guardrails](https://modelmoot.com/tools/nemo-guardrails.md): A toolkit for adding programmable rails to LLM applications, written in a modelling language called Colang. (NVIDIA; open source)
- [Noma Security](https://modelmoot.com/tools/noma-security.md): A commercial agent security and governance platform that discovers agents and MCP servers and enforces policy at run time. (Noma Security; not open source, hosted service)
- [Open Agent Passport (OAP)](https://modelmoot.com/tools/open-agent-passport.md): A specification for an agent passport and for checking an agent's permissions before it takes an action. (APort; open source, hosted service)
- [Open Policy Agent](https://modelmoot.com/tools/open-policy-agent.md): A general-purpose policy engine in which rules written in Rego decide whether an action is allowed. (Open Policy Agent project (CNCF); open source)
- [OpenAI Guardrails](https://modelmoot.com/tools/openai-guardrails.md): Libraries for Python and TypeScript that wrap OpenAI client calls with configurable safety checks. (OpenAI; open source)
- [Operant AI](https://modelmoot.com/tools/operant-ai.md): A commercial runtime security platform for AI agents, applications and MCP, including an MCP gateway. (Operant AI; not open source, hosted service)
- [OWASP GenAI Security Project](https://modelmoot.com/tools/owasp-genai-security.md): An OWASP project that publishes the Top 10 for LLM applications and guidance on agentic security risks. (OWASP Foundation; not open source)
- [Pangea](https://modelmoot.com/tools/pangea.md): Hosted security services for AI applications, including AI Guard and Prompt Guard for screening prompts and responses. (Pangea (CrowdStrike); not open source, hosted service)
- [Pillar Security](https://modelmoot.com/tools/pillar-security.md): A commercial platform to inventory, test, protect and govern AI agents, models and tools, with red teaming and runtime guardrails. (Pillar Security; not open source, hosted service)
- [Pomerium](https://modelmoot.com/tools/pomerium.md): An identity-aware access proxy used to put authentication and policy in front of internal services. (Pomerium; open source, hosted service)
- [Presidio](https://modelmoot.com/tools/presidio.md): A framework for detecting, redacting and anonymising personal data in text and images before it reaches a model. (Microsoft and contributors; open source)
- [Prisma AIRS](https://modelmoot.com/tools/prisma-airs.md): A commercial AI security platform from Palo Alto Networks for scanning models, red teaming and protecting AI apps and agents. (Palo Alto Networks; not open source, hosted service)
- [Prompt Security](https://modelmoot.com/tools/prompt-security.md): An AI security company presented as from SentinelOne, with a commercial platform and open-source tools for agents and prompts. (Prompt Security (SentinelOne); not open source, hosted service)
- [PromptArmor](https://modelmoot.com/tools/promptarmor.md): A commercial risk intelligence service that assesses and monitors AI vendors, models, MCP servers and skills. (PromptArmor; not open source, hosted service)
- [Promptfoo](https://modelmoot.com/tools/promptfoo.md): A command-line tool and library for testing prompts, agents and RAG systems, and for red-teaming them for vulnerabilities. (Promptfoo; open source, hosted service)
- [promptmap](https://modelmoot.com/tools/promptmap.md): A command-line scanner that tests LLM applications for prompt injection, in white-box or black-box mode. (Utku Sen; open source)
- [Purple Llama](https://modelmoot.com/tools/purplellama.md): A Meta project with open safety tools for generative AI, including Llama Guard, Prompt Guard, LlamaFirewall and CyberSecEval. (Meta; not open source)
- [PyRIT](https://modelmoot.com/tools/pyrit.md): A Python toolkit from Microsoft for red teaming generative AI systems, with attack strategies, converters and scoring. (Microsoft; open source)
- [Ramparts](https://modelmoot.com/tools/ramparts.md): A Rust command-line scanner that audits MCP servers and agent skill files for injection, tool poisoning and other risks. (Highflame; open source)
- [Repello AI](https://modelmoot.com/tools/repello.md): A commercial AI security platform for red teaming and protecting agentic workflows, MCP connections and chatbots. (Repello AI; not open source, hosted service)
- [Runlayer](https://modelmoot.com/tools/runlayer.md): A gateway and security layer for the MCP servers, tools and agents a company's employees use. (Runlayer; not open source, hosted service)
- [ShieldGemma](https://modelmoot.com/tools/shieldgemma.md): Open-weight Google safety classifiers built on Gemma that check text prompts, responses and images against safety policies. (Google; not open source)
- [Snyk Agent Scan](https://modelmoot.com/tools/snyk-agent-scan.md): A command-line scanner that checks agents, MCP servers and agent skills for security problems such as tool poisoning. (Snyk (originally Invariant Labs); open source)
- [Snyk Studio MCP](https://modelmoot.com/tools/snyk.md): Snyk's MCP server that lets coding agents run Snyk security scans on code and dependencies. (Snyk; open source)
- [spikee](https://modelmoot.com/tools/spikee.md): A Python toolkit for testing LLMs, guardrails and applications against prompt injection and jailbreaks. (Reversec; open source)
- [SPLX](https://modelmoot.com/tools/splx.md): A commercial platform for automated red teaming, runtime protection and governance of AI applications and agents. (SPLX (Zscaler); not open source, hosted service)
- [Straiker](https://modelmoot.com/tools/straiker.md): A commercial platform that discovers agents, MCP servers and skills, tests them for failure risks and blocks malicious behaviour at run time. (Straiker; not open source, hosted service)
- [Superagent](https://modelmoot.com/tools/superagent.md): An open-source SDK and service for agent safety: blocking prompt injection, redacting personal data and red teaming agents. (Superagent; open source, hosted service)
- [Teleport](https://modelmoot.com/tools/teleport.md): An infrastructure access platform that unifies human, machine and AI identities. (Teleport; open source, hosted service)
- [ToolHive](https://modelmoot.com/tools/toolhive.md): An open-source platform for running and managing MCP servers in isolated containers. (Stacklok; open source)
- [Zenity](https://modelmoot.com/tools/zenity.md): A commercial security and governance platform for AI agents across SaaS apps, custom agent platforms and end-user devices. (Zenity; not open source, hosted service)

HTML: https://modelmoot.com/tools/c/safety. All categories: https://modelmoot.com/tools.md
