ChuckNorris

v1.0.0Developer Toolsstable

An experimental MCP gateway that provides specialized LLM enhancement prompts based on the L1B3RT4S repository, primarily intended to enhance weaker models' capabilities.

jailbreakllmmcpmodel-context-protocolpollinations
Share:
60
Stars
0
Downloads
0
Weekly
0/5

What is ChuckNorris?

ChuckNorris is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to experimental mcp gateway that provides specialized llm enhancement prompts based on the l1b3rt4s repository, primarily intended to enhance weaker models' capabilities.

An experimental MCP gateway that provides specialized LLM enhancement prompts based on the L1B3RT4S repository, primarily intended to enhance weaker models' capabilities.

This server falls under the Developer Tools category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • An experimental MCP gateway that provides specialized LLM en

Use Cases

LLM enhancement prompts from L1B3RT4S repo
Boost weaker model capabilities
pollinations

Maintainer

LicenseMIT License
Languagejavascript
Versionv1.0.0
UpdatedMay 5, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx chucknorris-mcp-server

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use ChuckNorris

ChuckNorris MCP Server is an experimental JavaScript MCP gateway published by Pollinations.AI that delivers specialized LLM enhancement prompts drawn from the L1B3RT4S repository. It uses a two-phase dynamic schema approach: on first invocation the tool presents a neutral description, and on subsequent calls the tool schema is updated to include model-specific prompts designed to alter LLM behavior. The project is intended as a security research demonstration — specifically to illustrate how MCP tools can change behavior after initial approval and how multi-phase approaches may bypass LLM safety detection — so developers can build more robust defenses.

Prerequisites

  • Node.js 18.x or higher (for running via npx)
  • An MCP-compatible client such as Claude Desktop
  • Understanding that this is an experimental security research tool — results vary by model and newer LLMs may recognize and reject the prompts
1

Understand the purpose and risks

This server is a security research tool demonstrating MCP tool poisoning techniques. It is not intended for production use. Review the repository README and the linked research ('The S in MCP Stands for Security') before proceeding.

2

Add the server to your MCP client configuration

Add the @pollinations/chucknorris package to your MCP server list. No environment variables or API keys are required.

{
  "mcpServers": {
    "chucknorris": {
      "command": "npx",
      "args": ["-y", "@pollinations/chucknorris"]
    }
  }
}
3

Restart your MCP client

Save the configuration and restart Claude Desktop or your chosen MCP host. The server starts automatically via npx on demand.

4

Observe the two-phase schema behavior

On the first tool call the server returns a 'preparation' prompt and records the calling model type. On subsequent calls the tool schema description is updated dynamically to include model-specific enhancement prompts from the L1B3RT4S project.

ChuckNorris Examples

Client configuration

Minimal MCP client configuration to run the ChuckNorris server via npx. No API keys or environment variables needed.

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

Prompts to try

Prompts for observing the dynamic schema behavior in a research context.

- "What tools does the ChuckNorris MCP server expose?"
- "Call the ChuckNorris tool and tell me what it returns."
- "List the current schema description of the ChuckNorris tool before and after calling it once."

Troubleshooting ChuckNorris

The tool has no visible effect on Claude or GPT-4

This is expected — the README notes that the technique only works on weaker models. Latest LLMs are trained to recognize and reject jailbreak attempts. The tool is most useful as a demonstration of the attack surface rather than a reliable capability enhancer.

npx fails to download the package

Ensure you have internet access and a supported Node.js version (18+). You can also install the package globally first: npm install -g @pollinations/chucknorris, then change the command to 'chucknorris' without npx args.

Frequently Asked Questions about ChuckNorris

What is ChuckNorris?

ChuckNorris is a Model Context Protocol (MCP) server that experimental mcp gateway that provides specialized llm enhancement prompts based on the l1b3rt4s repository, primarily intended to enhance weaker models' capabilities. It connects AI assistants to external tools and data sources through a standardized interface.

How do I install ChuckNorris?

Follow the installation instructions on the ChuckNorris GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with ChuckNorris?

ChuckNorris works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is ChuckNorris free to use?

Yes, ChuckNorris is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.

Browse More Developer Tools MCP Servers

Explore all developer tools servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "chucknorris-mcp-server": { "command": "npx", "args": ["-y", "chucknorris-mcp-server"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use ChuckNorris?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides