AI agents call query_chef_server to retrieve information from SousChef without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The name indicates a data retrieval operation against a Chef server, which is a Read category action. However, the severity is elevated to medium rather than low because Chef servers often contain sensitive infrastructure configuration data, secrets references, and deployment information that could be valuable to an attacker if exfiltrated.
From the tool's definition Tool name is 'query_chef_server' with prefix 'query' which typically retrieves data. No description provided to confirm extent of access.
Documented attack patterns abuse exactly the kind of access query_chef_server 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 query_chef_server:
{
"version": "1",
"default": "deny",
"tools": {
"query_chef_server": {}
}
}query_chef_server is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
query_chef_server. It is categorised as a Read tool in the SousChef MCP Server, which means it retrieves data without modifying state.
Register the SousChef MCP server in PolicyLayer and add a rule for query_chef_server: 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.
query_chef_server is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the query_chef_server 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 query_chef_server. 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.
query_chef_server 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.