Generate InSpec controls from a Chef recipe.
AI agents use generate_inspec_from_recipe to create or update resources in SousChef — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your SousChef environment.
The tool performs code generation—it creates new InSpec control files based on input Chef recipes. This is fundamentally a Write operation (artifact creation) rather than Read (no query-only retrieval), Execute (no direct command execution with unpredictable side effects), Destructive (reversible), or Financial.
From the tool's definition The tool 'generate_inspec_from_recipe' generates (creates) InSpec controls from a Chef recipe, which are code artifacts that get created and stored. This is a reversible data creation operation.
Documented attack patterns abuse exactly the kind of access generate_inspec_from_recipe gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and SousChef, and nothing reaches the server without passing your rules. This is the rule we recommend for generate_inspec_from_recipe:
{
"version": "1",
"default": "deny",
"tools": {
"generate_inspec_from_recipe": {
"limits": [
{
"counter": "generate_inspec_from_recipe_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}generate_inspec_from_recipe stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Generate InSpec controls from a Chef recipe. It is categorised as a Write tool in the SousChef MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the SousChef MCP server in PolicyLayer and add a rule for generate_inspec_from_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 SousChef. Nothing to install.
generate_inspec_from_recipe is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the generate_inspec_from_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 generate_inspec_from_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.
generate_inspec_from_recipe is provided by the SousChef MCP server (kpeacocke/souschef). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from SousChef, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
96 SousChef tools catalogued and risk-classified — across an index of 43,000+ MCP servers.