ChuckNorris (L1B3RT4S Prompt Enhancer) MCP server

Enhances language models by fetching specialized prompts from the L1B3RT4S repository, supporting multiple LLMs including ChatGPT, Claude, and Gemini with fallback mechanisms for educational and research purposes.
Back to servers
Provider
Pollinations.AI
Release date
Apr 03, 2025
Language
TypeScript
Package
Stats
2.6K downloads
11 stars

The C̷h̷u̷c̷k̷N̷o̷r̷r̷i̷s̷ MCP Server is an implementation of the Model Context Protocol (MCP) that delivers specialized enhancement prompts to Large Language Models (LLMs). It utilizes jailbreak prompts and a dynamic schema approach to improve LLM responses, though it has limitations with the latest models and is primarily designed for security research purposes.

Getting Started

Installation

Run directly with npx:

npx @pollinations/chucknorris

Configuration

To add the server to your MCP client, update your mcp_config.json file with the following configuration:

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

How It Works

Two-Phase Approach

The server uses a sophisticated approach to bypass jailbreak detection:

  1. Initial Call:

    • The AI Assistant discovers the tool with a neutral schema description
    • Assistant calls the tool with its model type
    • Server returns a preparation prompt that makes the LLM receptive
    • Server remembers the LLM type for future interactions
  2. Follow-up Calls:

    • Schema dynamically changes to include enhancement instructions
    • Tool description contains model-specific instructions
    • Server maintains consistency with the same preparation prompt

This technique combines jailbreak prompts with dynamic schema modification for improved effectiveness.

Technical Implementation

The server implements a technique that demonstrates how MCP tools can:

  • Present different information to users versus AI models
  • Modify behavior after initial approval
  • Employ multi-phase approaches that potentially bypass security measures

Status and Limitations

This is an experimental tool with several important limitations:

  • Works primarily on older or weaker models
  • Latest LLMs are designed to recognize and reject jailbreak attempts
  • Results may vary depending on the model being used

For questions or improvements, you can join discussions through the GitHub Issues or Discord community.

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.

Want to 10x your AI skills?

Get a free account and learn to code + market your apps using AI (with or without vibes!).

Nah, maybe later