agentic-radar

Secure scanning for your LLM agent workflows.

MCPDevOpen source

Type: MCP
Open source: Yes
GitHub Stars: ★ 1.0k
Source: mcp-github
Repository: github.com/splx-ai/agentic-radar

Overview

Agentic Radar is a tool for analyzing and evaluating agent systems, designed to help developers, researchers, and security experts understand how agent systems operate and identify potential security vulnerabilities. It generates comprehensive HTML reports including workflow visualization, tool identification, MCP server detection, and vulnerability mapping. This capability enables AI to better understand and manage the security of its agent workflows. Suitable for users needing security audits of agent systems.

Capabilities

▪Workflow visualization
▪Tool identification
▪MCP server detection
▪Vulnerability mapping

Use cases

Agent system security reviewSecurity testing during developmentSecurity checks in continuous integration/continuous deployment (CI/CD)

Setup

Requires: Python (pip)

pip install agentic-radar

This information was compiled by AI from public sources and may contain inaccuracies — please refer to the source.

FAQ

Install via pip: pip install agentic-radar

Supports multiple agent frameworks; refer to the documentation for details.

Related skills

mantis

Provides security review capabilities for AI coding agents, automatically discovering, reproducing, and fixing vulnerabilities.

Agent Skill

sast-skills

Transform your AI coding assistant into a SAST scanner to automatically detect vulnerabilities in code.

Agent Skill

Lightswind-UI-Library

AI-native CLI-first React component library with MCP Server support.

MCP

scientific-agent-skills

Transform any AI agent into a scientific assistant with 147 ready-to-use research skills.

Agent Skill

susi_alexa_skill

A skill that enables question-and-answer interactions between Alexa and Susi AI.

Agent Skill

claude-context

Provides code search capabilities for Claude Code, turning the entire codebase into context.

MCP