Runtime Security Python Packages

insa-its

Runtime Security for Multi-Agent AI — Website & Documentation

mobsf

Mobile Security Framework (MobSF) is an automated, all-in-one mobile application (Android/iOS/Windows) pen-testing, malware analysis and security assessment framework capable of performing static and dynamic analysis.

mcp-rampart

Security toolkit for FastAPI-based MCP servers — pre-flight audit + runtime prompt-injection guardrail. 97M MCP installs/month — someone has to audit what they expose.

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.

cerberus-ai

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

bluerock-oss

Rust DSO backend for BlueRock — handles NDJSON event writing for the bluerock Python sensor

omega-walls

Omega Walls — a deterministic runtime trust boundary for RAG and AI agents that models cumulative prompt-injection, secret-exfiltration, and tool-abuse pressure before untrusted content reaches context or tools.

pyrasp

PyRASP is a Runtime Application Self Protection package for Python-based Web Servers (Flask, FastAPI and Django), Serverless Functions (AWS Lambda, Azure and Google Cloud Functions) and MCP Servers (FastMCP)

agentguardx

Runtime security layer for AI agents — inspect, control, and audit every tool call. Trust-aware data flow, 3-layer intent consistency detection, Merkle audit trail. Drop-in support for LangChain, CrewAI, AutoGen, OpenClaw, MCP, Dify, AutoGPT, n8n.

orchesis

Transparent HTTP proxy for AI agents. Block threats, cut token waste, monitor your fleet. Zero code changes. MIT license.

policyshield

Declarative firewall for OpenClaw tool calls.

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 2.0

agentshield-runtime

Runtime security layer for AI agents — inspect, control, and audit every tool call. Trust-aware data flow, 3-layer intent consistency detection, Merkle audit trail. Drop-in support for LangChain, CrewAI, AutoGen, OpenClaw, MCP, Dify, AutoGPT, n8n.

prooflayer-runtime

Open-source runtime security rules engine for MCP servers and AI agents. Detects prompt injection, command injection, jailbreaks, and data exfiltration.

sudoagent

A runtime authorization layer for LLM tool calls policy, approval, audit logs.