Scan agentic codebases for exposed tools MCP usage and mapped security findings with Agentic Radar
Generate a reviewable security report for a supported agent workflow before deployment by scanning its code, tools, MCP usage, and known vulnerability surface.
Prerequisites
Python with pip, Agentic Radar CLI, a supported agent framework codebase such as LangGraph, CrewAI, n8n, OpenAI Agents, or AutoGen, local shell access
Installation
Use the upstream install or setup path that matches your environment:
- pip install agentic-radar
- pip install "agentic-radar[crewai]"
- pip install "agentic-radar[openai-agents]"
Requirements and caveats from upstream:
- There are none! Just make sure you have Python (pip) installed on your machine.
- Some features require extra installations, depending on the targeted agentic framework. See more below.
Basic usage or getting-started notes:
Getting Started
Extracted from upstream docs: https://raw.githubusercontent.com/splx-ai/agentic-radar/HEAD/README.md