AI agents call where_on_atlas to retrieve information from Epicure MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool operates within a public, anonymous, read-only server for culinary ingredient analysis. All sibling tools are Read operations (querying embeddings, finding correlations, listing factors). The tool name implies a query or lookup operation rather than modification, deletion, or execution.
From the tool's definition Tool is part of a read-only MCP server ('read-only') with sibling tools that perform queries and analysis (find_pairings, flavour_correlations, neighbors, closest_mode).
Documented attack patterns abuse exactly the kind of access where_on_atlas gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Epicure MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for where_on_atlas:
{
"version": "1",
"default": "deny",
"tools": {
"where_on_atlas": {}
}
}where_on_atlas 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.
where_on_atlas. It is categorised as a Read tool in the Epicure MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Epicure MCP Server MCP server in PolicyLayer and add a rule for where_on_atlas: 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 Epicure MCP Server. Nothing to install.
where_on_atlas 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 where_on_atlas 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 where_on_atlas. 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.
where_on_atlas is provided by the Epicure MCP Server MCP server (kaikaku-ai/epicure-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Epicure MCP Server, 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.
13 Epicure MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.