Get the FREE Ultimate OpenClaw Setup Guide →

agentic-radar

A security scanner for your LLM agentic workflows

Installation
Run this command in your terminal to add the MCP server to Claude Code.
Run in terminal:
Command
claude mcp add --transport stdio splx-ai-agentic-radar python -m agentic_radar

How to use

Agentic Radar is a security analysis tool for agentic workflows. It scans systems to produce a comprehensive HTML report that visualizes agentic workflows, identifies tools in use (external and custom), maps detected MCP servers, and correlates potential vulnerabilities with known security frameworks. The CLI provides two core commands: scan and test. Use scan to analyze a project’s workflow graph and generate a report, for example by point­ing the tool at a language graph, CrewAI workflows, or OpenAI Agents assets. Use test to run vulnerability assessments on an agentic workflow, which requires an OpenAI API key to run the checks across the selected framework. Advanced usage includes enabling optional extras (like CrewAI or OpenAI Agents integrations) for deeper tool descriptions and richer vulnerability mappings.

How to install

Prerequisites:

  • Python 3.8+ and pip installed on your system

Install Agentic Radar:

pip install agentic-radar

Verify installation:

agentic-radar --version

Optional advanced installations:

  • CrewAI enhancements (requires CrewAI support in your environment):
    pip install "agentic-radar[crewai]"
    
  • OpenAI Agents enhancements (for richer OpenAI Agents integration):
    pip install "agentic-radar[openai-agents]"
    

Usage after installation is ready via the CLI as described in the next section.

Additional notes

Notes and tips:

  • To run vulnerability tests, you must set OPENAI_API_KEY in your environment.
  • Some features depend on external tool integrations (e.g., CrewAI, OpenAI Agents). Install the corresponding extras if you plan to use those features.
  • The MCP server setup in this repo uses the Python package entry point; ensure your Python environment has access to the agentic-radar executable in your PATH when invoking the MCP server via MCP tooling.
  • If you encounter permission errors on installation, consider using a virtual environment (venv) to isolate dependencies.
  • The tool generates an HTML report that you can view in a browser; for long-running scans, ensure your environment supports the required resources for graph rendering and vulnerability mapping.

Related MCP Servers

Sponsor this space

Reach thousands of developers