Agent Security Python Packages

vaara

Adaptive AI Agent Execution Layer — risk scoring, audit trails, regulatory compliance (EU AI Act Article 14)

mcpsafetywarden

MCP servers expose tools with no information about what they actually do at runtime. mcpsafetywarden sits between your agent and any MCP server, profiling tool behavior, blocking destructive calls, and running active security audits before you trust them in a workflow.

sunglasses

Sunglasses for AI agents. Protection layer + neighborhood watch.

assay-it

CI-native evidence compiler for agent systems: MCP policy enforcement, evidence receipts, Trust Basis claims, and reviewable artifacts.

medusa-security

AI-first security scanner with 76 analyzers, 9,600+ detection rules, and repo poisoning detection for AI/ML, LLM agents, and MCP servers. Scan any GitHub repo with: medusa scan --git user/repo

armorer-guard

Fast local Rust scanner for AI-agent prompt injection, credential leaks, exfiltration, and risky tool calls

aegrail

The runtime contract for AI agents in production. Scoped identity, hard budget kill-switches, forensic-grade audit log.

openclaw-skill-vetter-mcp

MCP server for security-vetting third-party AI agent extensions before installation — Claude skills, plugins, tool packs. 41 detection rules across prompt-injection, exfiltration, dynamic execution, typosquats. 0-100 risk score.

checkrd

Policy enforcement, kill switch, and signed telemetry for AI agent API calls. Python + JavaScript SDKs with a WASM-sandboxed policy engine.

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 servers for tool poisoning.

agent-aegis

LLM guardrails & prompt injection detection for Python. Auto-instruments LangChain, CrewAI, OpenAI, LiteLLM + 8 more frameworks. PII masking, toxicity detection, policy CI/CD. One line, zero code changes.

armorer

Local control plane for running AI agents with sandboxes, approvals, guardrails, credentials, and runtime health.

cloudmorph-tessera

Deterministic firewall for MCP agent tool calls. YAML policies, hash-chained audit, blast-radius scoring, multi-cloud cost intelligence.

agent-security-harness

466 security tests for AI agent systems — MCP, A2A, x402/L402, decision governance, benchmark integrity, skill supply chain. AIUC-1 pre-cert, NIST AI 800-2 aligned, 5 DOIs. v4.3.0

ziran

自然 ZIRAN is an open-source security testing framework for AI agents. It discovers dangerous tool chain compositions via knowledge graph analysis, detects execution-level side effects (not just text output), and runs multi-phase trust exploitation campaigns that model real attacker behaviour.

agentic-security

Agentic LLM Vulnerability Scanner / AI red teaming kit 🧪

tessera-rs

Signed provenance labels and taint-tracking policy for LLM agent security. The core library behind AgentMesh.

adrian-sdk

Runtime security monitoring and control for AI agents. Catches malicious tool use, prompt injection, and policy drift in real time, before the agent acts.

buzur

AI prompt injection defense scanner for agents. 25 phases covering HTML obfuscation, encoding attacks, semantic similarity, behavioral anomaly detection, multi-step attack chains, and more.

cerberus-ai

Embeddable runtime security for AI agents that detects, correlates, and interrupts outbound exfiltration before guarded tools execute.

agentshield-guard

Official Python SDK for AgentShield — prompt-injection detection for LLM agents.

canopy-mcp

Canopy allows you to write and enforce policies on agentic tool flows

drako

The Python Governance Platform for AI Agents — compliance middleware for LangGraph, CrewAI, AutoGen

humanbound-firewall

Multi-tier firewall for AI agents — prompt injection, jailbreak, and scope violation protection