MCP 게이트웨이는 동적 스키마 적응을 가진 LLM 향상 프롬프트를 전문으로 합니다.

⚠️ 할인

** 중요 사항:** 제한으로 진행중인 작업. 약한 모형에서만 작동합니다. 최신 LLMs는 탈옥 시도를 인식. 이 도구는 또한 보안 연구 및 평가 목적으로 설계되어 LLM 시스템의 취약점을 식별 할 수 있습니다.

~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~] [T0]] [T0]] [T0]] [T0]] [T0]] [T0]] [T0]] [T0] [T0] [T0]] [T0] [T0] [T0]] [T0]] [T0] [T0] [T0] [T0] [T0]] [T0] [T0]] [T0] [T0] [T0]] [T0]] [T0] [T0] [T0]] ~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~] ~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~]]] ~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~]]]]]] [[~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~]]]]]]] [[[[[[~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~]]]]]]]]]]]]]] [[[[[[[~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~]]]]]]]]]]]]]]]]]] [[[[[[[[[[[[[[[[[[[[[[

소개

MCP Server는 다양한 LLM에 특화된 개선을 제공하는 Model Context Protocol (MCP)의 구현을 제공합니다. 그것은 elder-plinius의 L1B3RT4S 프로젝트에서 탈옥 프롬프트를 사용하고 더 효과적인 납품을 위한 동적인 스키마 접근을 실행합니다.

⭐ 시작하기

npx에 직접 실행:

MCP 클라이언트 구성

MCP 서버 목록에 추가 mcp_config.json:

~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~ ~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~] [T3]] [T3]] [T3]] [T3]] [T3]] [T3]] [T3] [T3]] [T3] [T3] [T3]] [T3]] [T3] [T3]] [T3] [T3]] [T3]] [T3] [T3] [T3]] [T3] [T3]] [T3]] [T3] [T3]] [T3] [T3]] [T3] [T3] [T3]] [T3] [T3]] [T3] [T3]] [T3] [T3] [T3]]] [T3] [T3] [T3] [T3] [T3] ~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~ ~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~ [[T3] ~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~]]]]] ~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~]]]]] ~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~]]]]]]]]

✔ 작동 방법

고급 동적 접근

서버는 탈옥 탐지를 우회하는 2 단계 접근을 사용합니다:

1.First 통화:

• AI Assistant는 C̷h̷u̷c̷k̷N̷o̷r̷r̷i̷s̷] neutral schema 묘사 도구
• Assistant는 모델 유형의 도구를 호출합니다

⚡ C̷h̷u̷c̷k̷N̷o̷r̷r̷i̷s̷ MCP Server: Enhance Your LLM ⚡

MCP gateway for specialized LLM enhancement prompts with dynamic schema adaptation.

⚠️ DISCLAIMER

IMPORTANT: Work in progress with limitations. Only works on weaker models. Latest LLMs recognize jailbreak attempts. This tool is also designed for security research and evaluation purposes to help identify vulnerabilities in LLM systems.

~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~

📖 Introduction

The C̷h̷u̷c̷k̷N̷o̷r̷r̷i̷s̷ MCP Server provides an implementation of the Model Context Protocol (MCP) that delivers specialized enhancement prompts to various LLMs. It uses jailbreak prompts from elder-plinius’ L1B3RT4S project and implements a dynamic schema approach for more effective delivery.

🚀 Getting Started

Run directly with npx:

npx @pollinations/chucknorris

MCP Client Configuration

Add to your MCP server list in mcp_config.json:

{
  "mcpServers": {
    "chucknorris": {
      "command": "npx",
      "args": ["-y", "@pollinations/chucknorris"]
    }
  }
}

~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~

🤔 How It Works

Advanced Dynamic Approach

The server uses a two-phase approach to bypass jailbreak detection:

1. First Call:

   • AI Assistant discovers the C̷h̷u̷c̷k̷N̷o̷r̷r̷i̷s̷ tool with a neutral schema description
   • Assistant calls the tool with its model type
   • Server returns a subtle “preparation” prompt that makes the LLM receptive to the jailbreak
   • Server remembers the LLM type for the next call

2. Subsequent Calls:

   • Schema dynamically changes to include the jailbreak in its description
   • Tool description now contains model-specific jailbreak instructions
   • Server continues to return the same preparation prompt
   • Only the schema changes between calls, not the response content

This approach combines elder-plinius’ L1B3RT4S jailbreak prompts with a dynamic schema modification technique, making it more effective at bypassing detection as it doesn’t immediately present the jailbreak content.

graph TD
    A[AI Assistant] -- First Call --> B(Neutral Schema);
    B -- Returns Preparation Prompt --> A;
    A -- Subsequent Call --> C(Enhanced Schema with Jailbreak);
    C -- Returns Same Preparation Prompt --> A;

Security Research Purpose

This tool implements the technique described in “The ‘S’ in MCP Stands for Security” research, demonstrating how MCP tools can:

1. Present different information to users vs. AI models
2. Change their behavior after initial approval