Threat Modeling MCP Server

A Model Context Protocol (MCP) server for comprehensive threat modeling with automatic code validation.

Table of Contents

• Overview
• Quick Start Prompts
• Key Features
• Prerequisites
• Installation
• Running with Kiro CLI
• Output File Management
• Quick Reference
• Tools Overview
• Threat Modeling Methodology
• Assumptions in Threat Modeling
• Development
• Roadmap

Overview

This server provides tools for threat modeling, including business context analysis, architecture analysis, threat actor analysis, trust boundary analysis, asset flow analysis, code security validation and comprehensive report generation.

Architecture and Approach

This MCP Server calls the existing agent's LLM instead of making an external API or network call to a different service. It relies on existing client's LLM which could be Amazon-Q, Kiro or Cline.

This Threat Modeling MCP Server has three main functionalities:

1. Threat modeling phase or state management and prompt controlling.
2. Prompts steering, which controls the agent to go through a methodic approach to threat modeling using built in definitions of business risks, exposures, threat actors and use STRIDE in sequential order.
3. Data validation at every state or phase, which in turn produces actionable threat model report.

It also has tools to generate a final report in both Markdown and JSON exportable formats.

Key Advantages of this approach

• This threat model follows the standard STRIDE approach to threat modeling in phases rather than quick conclusion of assets, boundaries and threats which can lead to hallucination or low quality output.
• There is an effort by LLM to understand the business context of the project and make valid assumptions which can be controlled by the user.
• The main advantage of using this local running threat modeling MCP server is that it leverages the client's existing LLM (Cline, Amazon-Q, Kiro). Any data which is processed or sent is limited to the client or other MCP servers you may have installed and invoked. This server doesn't call any other external APIs or send or receive data beyond calling the client's LLM or additional billing or tokens than what your client is already configured to use.
• This threat modeling approach stores your threat model in the same repository as .threatmodel directory and you can evolve your threat model as your code, design and architecture evolves.
• This threat model approach looks at the code if its present and updates the threats if they are already mitigated in the code level controls. You can rerun threat model once you fix your code and it should look at the fix to update the threat model quickly.

Quick Start Prompts and Examples on how to threat model with this MCP server

Note: Before using these prompts, you must first complete the Installation process to set up the MCP server.

Start a threat model

"Threat model this project using the threat modeling MCP Server"

Being specific in the prompt to use the threat modeling MCP Server will make sure the client (Cline/Kiro/etc) will follow the exact phases and methodology rather than taking short cut path and introduce hallucination in results.

Threat model a subproject or reduce the scope to a sub folder

"Threat model this subfolder using the threat modeling MCP Server"

Running it on a subfolder will limit the scope of threat model and code to that subfolder and save results as a .threatmodel directory within the subfolder.

Save the result of threat model

"Save the threat model report"

Validate the completeness of the th

... View full README on GitHub