Bake (execute) a recipe (a list of operations) in order to derive an outcome from the input data
AI agents invoke bake_recipe to trigger actions in CyberChef API MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool executes a user-defined sequence of CyberChef operations against supplied data. While CyberChef operations themselves are typically data-transformation utilities (encoding, decoding, hashing), the ability to execute arbitrary recipe sequences with external input creates execution risk. An agent could chain operations in unexpected ways or apply them to sensitive data.
From the tool's definition Tool description states 'Bake (execute) a recipe (a list of operations)' - the verb 'execute' and mention of running 'operations' in sequence indicates code/operation execution.
Documented attack patterns abuse exactly the kind of access bake_recipe gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and CyberChef API MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for bake_recipe:
{
"version": "1",
"default": "deny",
"tools": {
"bake_recipe": {
"limits": [
{
"counter": "bake_recipe_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}bake_recipe stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Bake (execute) a recipe (a list of operations) in order to derive an outcome from the input data. It is categorised as a Execute tool in the CyberChef API MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the CyberChef API MCP Server MCP server in PolicyLayer and add a rule for bake_recipe: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches CyberChef API MCP Server. Nothing to install.
bake_recipe is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the bake_recipe rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for bake_recipe. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
bake_recipe is provided by the CyberChef API MCP Server MCP server (slouchd/cyberchef-api-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 3 CyberChef API MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
3 CyberChef API MCP Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.