Collect user satisfaction rating for AI
AI agents call collect_rating to retrieve information from MCP-Confirm without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Collecting a satisfaction rating is purely informational—it retrieves user feedback without altering data, triggering actions, or causing irreversible changes. This falls squarely in the Read category. The severity is low because the tool only gathers subjective user input and poses minimal risk of misuse.
From the tool's definition The tool 'collect_rating' collects user satisfaction ratings. This is a query/retrieval operation that gathers user feedback without modifying system state, deleting data, or executing external commands.
Attacks that exploit this kind of access
Collect user satisfaction rating for AI. It is categorised as a Read tool in the MCP-Confirm MCP Server, which means it retrieves data without modifying state.
Register the MCP-Confirm MCP server in PolicyLayer and add a rule for collect_rating: 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 MCP-Confirm. Nothing to install.
collect_rating 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 collect_rating 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 collect_rating. 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.
collect_rating is provided by the MCP-Confirm MCP server (mako10k/mcp-confirm). 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 →