Cyberchef MCP

🚀 CyberChef MCP Server

This project offers a Model Context Protocol (MCP) server interface for CyberChef, known as the "Cyber Swiss Army Knife". It allows AI assistants such as Claude and Cursor AI to directly leverage CyberChef's more than 300 data manipulation operations, including encryption, encoding, compression, and forensic analysis, as executable tools.

🚀 Quick Start

Prerequisites

• Docker should be installed and running.

Installation & Usage

1. Build the Docker Image:

   docker build -f Dockerfile.mcp -t cyberchef-mcp .
   

2. Run the Server (Interactive Mode): This command starts the server and listens on stdin, which is what your MCP client will execute.

   docker run -i --rm cyberchef-mcp
   

✨ Features

MCP Tools

The server exposes CyberChef operations as MCP tools:

• cyberchef_bake: The "Omni - tool". It executes a complete CyberChef recipe (a sequence of operations) on an input, suitable for complex, multi - step transformations like "Decode Base64, then Gunzip, then prettify JSON".
• Atomic Operations: More than 300 individual tools for specific tasks, dynamically generated from the CyberChef configuration, such as cyberchef_to_base64 / cyberchef_from_base64, cyberchef_aes_decrypt, cyberchef_sha2, cyberchef_yara_rules, etc.
• cyberchef_search: A utility tool to assist the AI in discovering available operations and their descriptions.

Technical Highlights

• Dockerized: It runs as a lightweight, self - contained Docker container based on Alpine Linux.
• Stdio Transport: It communicates via standard input/output, facilitating integration with CLI - based MCP clients.
• Schema Validation: All inputs are validated against schemas derived from CyberChef's internal type system using zod.
• Modern Node.js: It is patched and configured to run on Node.js v22+.

📦 Project Context

CyberChef is a simple and intuitive web application for performing various "cyber" operations in a web browser. It was originally conceived and developed by GCHQ. This fork encapsulates the core CyberChef Node.js API into an MCP server, bridging the gap between natural language AI intent and deterministic data processing.

📚 Documentation

Detailed documentation can be found in the directory:

• : Provides detailed installation and client configuration instructions.
• : Lists all available MCP tools and operations.
• : Explains the technical design of the MCP server.

💻 Client Configuration

Cursor AI

1. Navigate to Settings > Features > MCP.
2. Add a new server:
   • Name: CyberChef
   • Type: command
   • Command: docker
   • Args: run -i --rm cyberchef-mcp

Claude Code (CLI)

Add the following to your configuration file:

{
  "mcpServers": {
    "cyberchef": {
      "command": "docker",
      "args": ["run", "-i", "--rm", "cyberchef-mcp"]
    }
  }
}

🔧 Development

Local Setup

If you want to modify the server code without using Docker:

1. Install Dependencies:

   npm install
   

2. Generate Config (Required to build the internal operation lists):

   npx grunt configTests
   

3. Run Server:

   npm run mcp
   

CI/CD

This project uses GitHub Actions to ensure stability:

• Core CI: Tests the underlying CyberChef logic and configuration generation on Node.js v22.
• Docker Build: Builds and verifies the cyberchef-mcp Docker image on every push.
• Release: Automatically publishes the Docker image to GHCR on version tags (v*).

🤝 Contributing

Contributions to the MCP adapter are welcome! Please refer to the to - dos/ directory for planned features and tasks. For contributions to the core CyberChef operations, please credit the original GCHQ repository.

📄 License

CyberChef is released under the Apache 2.0 Licence and is covered by Crown Copyright.