Composite tool: returns current pantry contents + dietary restrictions for named diners + a set of candidate recipes scored by
AI agents call meal_plan_from_pantry to retrieve information from Personal Brain without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a composite read/query tool that fetches and combines data from multiple sources (pantry, dietary prefs, recipes) to surface meal plan suggestions. No writes, executions, or destructive actions are described. Severity is low as misuse would only expose personal dietary/pantry information.
From the tool's definition 'returns current pantry contents + dietary restrictions for named diners + a set of candidate recipes scored by' — the tool retrieves and aggregates existing data (pantry contents, dietary restrictions, candidate recipes) without modifying anything
Attacks that exploit this kind of access
Composite tool: returns current pantry contents + dietary restrictions for named diners + a set of candidate recipes scored by. It is categorised as a Read tool in the Personal Brain MCP Server, which means it retrieves data without modifying state.
Register the Personal Brain MCP server in PolicyLayer and add a rule for meal_plan_from_pantry: 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 Personal Brain. Nothing to install.
meal_plan_from_pantry 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 meal_plan_from_pantry 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 meal_plan_from_pantry. 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.
meal_plan_from_pantry is provided by the Personal Brain MCP server (phantomts/personal-brain-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →