Get your notification and meal preferences
AI agents call get_preferences to retrieve information from IIITH Mess MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only retrieves user preference data without creating, modifying, deleting, or executing operations. It has minimal blast radius—an AI agent misusing it would only read the user's own preferences, posing no risk of data corruption, financial loss, or system compromise.
From the tool's definition Tool name 'get_preferences' and description 'Get your notification and meal preferences' indicate a retrieval operation with no side effects. The verb 'get' and absence of any modification language confirm this is a data query.
Attacks that exploit this kind of access
Get your notification and meal preferences. It is categorised as a Read tool in the IIITH Mess MCP Server MCP Server, which means it retrieves data without modifying state.
Register the IIITH Mess MCP Server MCP server in PolicyLayer and add a rule for get_preferences: 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 IIITH Mess MCP Server. Nothing to install.
get_preferences 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_preferences 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_preferences. 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_preferences is provided by the IIITH Mess MCP Server MCP server (njp6969/iiith-mess-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 →