Submit anonymous feedback for a meal. User must have availed the meal.
AI agents use mess_provide_feedback to create or update resources in IIITH Mess MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your IIITH Mess MCP environment.
This tool creates/submits feedback data. It's a Write operation with minimal blast radius — it only posts feedback tied to meals the user has already consumed. No financial, destructive, or execution aspects are present.
From the tool's definition Submit anonymous feedback for a meal
Documented attack patterns abuse exactly the kind of access mess_provide_feedback gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and IIITH Mess MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for mess_provide_feedback:
{
"version": "1",
"default": "deny",
"tools": {
"mess_provide_feedback": {
"limits": [
{
"counter": "mess_provide_feedback_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
} mess_provide_feedback 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.
Free to start. No card required.
Submit anonymous feedback for a meal. User must have availed the meal. It is categorised as a Write tool in the IIITH Mess MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the IIITH Mess MCP server in PolicyLayer and add a rule for mess_provide_feedback: 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. Nothing to install.
mess_provide_feedback 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 mess_provide_feedback 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 mess_provide_feedback. 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.
mess_provide_feedback is provided by the IIITH Mess MCP server (kallind/iiith-mess-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from IIITH Mess MCP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
45 IIITH Mess MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.