mealie_recipes_search
AI agents call mealie_recipes_search to retrieve information from Mealie MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
A search tool retrieves recipe data without modifying, deleting, or executing external operations. The primary blast radius is negligible—misuse would only return unwanted recipe information. The 'search' verb and read-oriented server context (searching recipes, listing categories) strongly indicate this is a passive data retrieval tool with no side effects.
From the tool's definition Tool name 'mealie_recipes_search' indicates a search operation. No description provided, but the sibling tools and server context (recipe management, meal planning) confirm this is a data retrieval function.
Attacks that exploit this kind of access
mealie_recipes_search. It is categorised as a Read tool in the Mealie MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Mealie MCP Server MCP server in PolicyLayer and add a rule for mealie_recipes_search: 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.
mealie_recipes_search 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 mealie_recipes_search 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 mealie_recipes_search. 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.
mealie_recipes_search is provided by the Mealie MCP Server MCP server (mdlopresti/mealie-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 →