AI agents call get_recommendations to retrieve information from Sendameal without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves meal product recommendations, likely filtered by context like occasion or user preferences. This is a retrieval operation with no side effects—no data is created, modified, or deleted. Despite the empty description reducing confidence slightly, the server's stated purpose (search, filter, recommend) and sibling tool patterns strongly indicate a Read classification.
From the tool's definition Tool name 'get_recommendations' and server context indicate querying/retrieving product recommendations without modifying data. Sibling tools (find_dietary_options, get_product_details, search_products) are all Read operations.
Attacks that exploit this kind of access
get_recommendations. It is categorised as a Read tool in the Sendameal MCP Server, which means it retrieves data without modifying state.
Register the Sendameal MCP server in PolicyLayer and add a rule for get_recommendations: 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 Sendameal. Nothing to install.
get_recommendations 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_recommendations 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_recommendations. 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_recommendations is provided by the Sendameal MCP server (mcshead/sendameal-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 →