Generate a 7-day structured eating plan for the current box, scheduling most perishable items earliest (Day 1 = delivery day)
AI agents call get_meal_plan to retrieve information from Mcp Veggie without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and analyzes existing information (current box state, perishability) to produce a structured recommendation. It has no side effects—it does not modify inventory, execute external operations, delete data, or move money. The action is purely analytical and advisory, fitting the Read category despite the word 'generate' in the name.
From the tool's definition Tool generates a structured plan based on current box contents, reading and organizing existing data. The description uses "generate" but the output is a meal plan (informational output), not creating persistent data, executing operations, or modifying box…
Attacks that exploit this kind of access
Generate a 7-day structured eating plan for the current box, scheduling most perishable items earliest (Day 1 = delivery day). It is categorised as a Read tool in the Mcp Veggie MCP Server, which means it retrieves data without modifying state.
Register the Mcp Veggie MCP server in PolicyLayer and add a rule for get_meal_plan: 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 Mcp Veggie. Nothing to install.
get_meal_plan 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 get_meal_plan 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 get_meal_plan. 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.
get_meal_plan is provided by the Mcp Veggie MCP server (lovettbarron/mcp-veggiebox). 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 →