Skip to main content
Glama
CyberChef API MCP Server

CyberChef API MCP Server

by slouchd

CyberChef API MCP Server

This model context protocol (MCP) server interfaces with the CyberChef Server API. Allowing you to use any LLM/MCP client of your choosing to utilise the tools and resources within CyberChef.

🧰 Available Tools and Resources

  • get_cyberchef_operations_categories: resource - gets updated Cyber Chef categories for additional context / selection of the correct operations

  • get_cyberchef_operation_by_category: resource - gets list of Cyber Chef operations for a selected category

  • bake_recipe: tool - bake (execute) a recipe (a list of operations) in order to derive an outcome from the input data

  • batch_bake_recipe: tool - bake (execute) a recipe (a list of operations) in order to derive an outcome from a batch of input data

  • perform_magic_operation: tool - perform CyberChef's magic operation which is designed to automatically detect how your data is encoded and which operations can be used to decode it

Related MCP server: CyberChef MCP Server

πŸ“ Usage

Start the server using the default stdio transport and specifying an environment variable pointing to a CyberChef API

CYBERCHEF_API_URL="your-cyberchef-api-url" uv run cyberchef_api_mcp_server

πŸ§‘β€πŸ’»Usage (Development)

Start the server and test it with the MCP inspector

uv add "mcp[cli]"
mcp dev server.py

πŸ“š Client Configuration

The following commands will generate a client configuration file, the location will depend on your operating system

uv add "mcp[cli]"
mcp install server.py --name "CyberChef API MCP Server"
TIP

After running the above command you can then tweak the client configuration to include the environment variable for the CyberChef API URL

{
 "mcpServers": {
   "CyberChef API MCP Server": {
     "command": "uv",
     "args": [
       "run",
       "--with",
       "mcp[cli]",
       "--directory",
       "cyberchef-api-mcp-server/cyberchef_api_mcp_server/",
       "mcp",
       "run",
       "server.py"
     ],
     "env": {
       "CYBERCHEF_API_URL": "your-cyberchef-api-url"
     }
   }
 }
}

πŸ” Demo

Using the MCP server in this example use case, the following prerequisites apply:

  • You must have Claude desktop installed

  • Have a running CyberChef API instance or one you are able to use

Here is a basic prompt being solved using the MCP server tools:

πŸ™‡ References

πŸͺͺ License

MIT License

Available Tools

3 tools
bake_recipeC
Bake (execute) a recipe (a list of operations) in order to derive an outcome from the input data

:param input_data: the data in which to perform the recipe operation(s) on
:param recipe: a pydantic model of operations to 'bake'/execute on the input data
:return:

Inputs: input_data (required), recipe (required).

batch_bake_recipeC
Bake (execute) a recipe (a list of operations) in order to derive an outcome from a batch of input data

:param batch_input_data: the batch of data in which to perform the recipe operation(s) on
:param recipe: a list of operations to 'bake'/execute on the input data
:return:

Inputs: batch_input_data (required), recipe (required).

perform_magic_operationB
CyberChef's magic operation is designed to automatically detect how your data is encoded and which operations can be
used to decode it

:param input_data: the data in which to perform the magic operation on
:param depth: how many levels of recursion to attempt pattern matching and speculative execution on the input data
:param intensive_mode: optional argument which will run additional operations and take considerably longer to run
:param extensive_language_support: if this is true all 245 languages are supported opposed to the top 38 by default
:param crib_str: argument for any known plaintext string or regex
:return:

Inputs: input_data (required), depth, intensive_mode, extensive_language_support, +1 more.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    B3.2/5.0

    Scored across 3 tools

    Disambiguation4/5

    bake_recipe and batch_bake_recipe are clearly distinct (single vs batch input), but their similarity could cause confusion. perform_magic_operation is distinct.

    Naming Consistency4/5

    All tools use snake_case and verb_noun pattern (bake_recipe, batch_bake_recipe, perform_magic_operation), though 'perform' is less typical than 'bake'.

    Tool Count4/5

    3 tools is slightly low but appropriate for a focused CyberChef wrapper; covers baking and magic detection without being overly minimal.

    Completeness3/5

    Covers core recipe execution and auto-detection, but missing tools for exploring available operations or constructing recipes, which are typical needs.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • F
      license
      Not graded
      quality
      D
      maintenance
      Enables AI agents to discover, execute, and validate CyberChef operations for data encoding, decoding, encryption, and transformation tasks. Provides structured access to CyberChef's extensive catalog of data manipulation tools through natural language interactions.
      -
    • A
      license
      B
      quality
      A
      maintenance
      GCHQ CyberChef's 504 data-transformation operations as MCP tools β€” encryption, encoding, compression and forensics β€” w/ 19 analysis tools for work a single operation cannot express, such as: hash identification, RSA and ECDSA attacks, XOR key-length recovery, cipher solving, X.509 chain validation and NIST post-quantum identification (ML-KEM/ML-DSA/SLH-DSA).
      23
      168 npm
      34
      GPL 3.0