remove_favorite
Remove a recipe from the current user's favorites.
This record as markdown: /tools/graysoncadams-mealie-mcp/remove-favorite.md
What remove_favorite does on Mealie MCP Server
AI agents use remove_favorite to create or update resources in Mealie MCP Server, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mealie MCP Server environment.
Why remove_favorite is rated Medium
Removing a favorite is a reversible write operation — the user can re-add the recipe to favorites at any time. It modifies user preference data but does not delete any recipe or permanent content, making it a low-severity write action.
From the tool's definition Remove a recipe from the current user's favorites
Attacks that exploit this kind of access
The rule that runs remove_favorite safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Mealie MCP Server, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For remove_favorite, this is the rule to start with:
remove_favorite stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Mealie MCP Server, apply this rule, and every remove_favorite call is checked against it from then on.
Questions about remove_favorite
Remove a recipe from the current user's favorites. It is categorised as a Write tool in the Mealie MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mealie MCP Server MCP server in PolicyLayer and add a rule for remove_favorite: 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 Mealie MCP Server. Nothing to install.
remove_favorite is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the remove_favorite 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 remove_favorite. 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.
remove_favorite is provided by the Mealie MCP Server MCP server (graysoncadams/mealie-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Mealie MCP Server, and thousands of servers like it.
This server
Across the catalogue