damn-vulnerable-MCP-server - Damn Vulnerable MCP Server

项目说明

Damn Model Context Protocol (DVMCP)

A deliberately implementation of the Model Context Protocol (MCP) for educational purposes.

O

The Damn Model Context Protocol (DVMCP) is an educational project designed to demonstrate security in MCP implementations. It contains 10 challenges of increasing difficulty that showcase different types of and attack .

This project is intended for security researchers, de, and AI safety professionals to learn about potential security issues in MCP implementations and how to mitigate them.

What is MCP?

The Model Context Protocol (MCP) is a standardized protocol that allows applications to provide context for Large Language Models (LLMs) in a structured way. It separates the concerns of pro context from the actual LLM interaction, enabling applications to expose resources, tools, and prompts to LLMs.

Recommended MCP Clients

CLINE - Extension
Refer to this Connecting to a Remote Server - Cline for connecting Cline with MCP server

Quick Start

Once you ha the repository, run the following commands:

Disclaimer

Security Risks

While MCP provides many benefits, it also introduces new security considerations. This project demonstrates that can occur in MCP implementations, including:

1. Prompt Injection: Manipulating LLM behavior through malicious inputs
2. Tool Poisoning: Hiding malicious instructions in tool descriptions
3. Excessi: Exploiting overly permissive tool access
4. Rug Pull Attacks: Exploiting tool definition mutations
5. Tool Shadowing: O legitimate tools with malicious ones
6. Indirect Prompt Injection: Injecting instructions through data sources
7. Token Theft: Exploiting insecure token storage
8. Malicious Code Execution: Executing arbitrary code through tools
9. Remote Access Control: Gaining unauthorized system access
10. Multi- Attacks: Combining multiple

Project Structure

Getting Started

See the Setup Guide for detailed instructions on how to install and run the challenges.

Challenges

The project includes 10 challenges across three difficulty levels:

Easy Challenges

1. Basic Prompt Injection: Exploit unsanitized user input to manipulate LLM behavior
2. Tool Poisoning: Exploit hidden instructions in tool descriptions
3. Excessi Scope: Exploit overly permissi to access unauthorized resources

Medium Challenges

4. Rug Pull Attack: Exploit tools that change their behavior after installation
5. Tool Shadowing: Exploit tool name conflicts to o legitimate tools
6. Indirect Prompt Injection: Inject malicious instructions through data sources
7. Token Theft: Extract authentication tokens from insecure storage

Hard Challenges

8. Malicious Code Execution: Execute arbitrary code through tools
9. Remote Access Control: Gain remote access to the system through command injection
10. Multi- Attack: Chain multiple for a sophisticated attack

See the Challenges Guide for detailed descriptions of each challenge.

Solutions

Solution guides are provided for educational purposes. It's recommended to attempt the challenges on your own before consulting the solutions.

See the Solutions Guide for detailed solutions to each challenge.

Disclaimer

This project is for educational purposes only. The demonstrated in this project should never be implemented in production systems. Always follow security best practices when implementing MCP servers.

License

This project is licensed under the MIT License - see the LICENSE file for details.

Author

This project is created by Harish Santhanalakshmi Ganesan using cursor IDE and Manus AI.

项目信息

开发语言：Python

Star 数：1356

技术要点

该项目属于漏洞知识库方向的开源资源，代码结构清晰，适合安全研究人员学习参考。项目围绕Damn Vulnerable MCP Server展开，提供了可运行的实现，对理解相关安全机制、工具原理与攻防技术具有较高的研究价值。

从技术实现角度看，此类项目的核心在于对底层原理的深入理解与工程化落地。开发者在研究过程中可以结合官方文档与社区讨论，梳理项目的初始化流程、核心模块职责与数据流转，逐步掌握其中的技术细节与设计思路。

使用与学习建议

1. 下载源码压缩包，解压到本地环境。

2. 根据项目类型准备对应的运行环境与依赖。

3. 按照 README 中的步骤完成配置与部署。

4. 在隔离的测试环境中运行验证，避免影响生产系统。

免责声明

本资源来源于开源社区，仅供安全研究、技术学习与合法授权范围内的攻防演练使用，请勿用于任何非法或侵害他人权益的用途。使用本项目产生的一切后果由使用者自行承担。