Fetch a meal-plan entry by numeric id.
AI agents call get_mealplan to retrieve information from Mcp Mealie without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves meal plan data by querying an existing resource using its numeric ID. It performs a read-only operation with no capacity to modify, create, delete, or execute code. The limited scope (single entry lookup) and inherent read-only nature warrant a 'low' severity classification.
From the tool's definition Tool name is 'get_mealplan' and description states 'Fetch a meal-plan entry by numeric id.' The verb 'Fetch' and the retrieval operation indicate data querying with no side effects.
Attacks that exploit this kind of access
Fetch a meal-plan entry by numeric id. It is categorised as a Read tool in the Mcp Mealie MCP Server, which means it retrieves data without modifying state.
Register the Mcp Mealie MCP server in PolicyLayer and add a rule for get_mealplan: 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 Mealie. Nothing to install.
get_mealplan 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_mealplan 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_mealplan. 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_mealplan is provided by the Mcp Mealie MCP server (obrien-matthew/mcp-mealie). 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 →