AI agents call list_feedback to retrieve information from Pelaris without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries feedback data without side effects or modifications. Even though it involves user data in a fitness coaching context, the read-only nature and PII scrubbing place it firmly in the Read category with low severity—a typical low-risk query operation.
From the tool's definition Tool name 'list_feedback' and description 'List user feedback entries' indicates data retrieval with no modification capabilities. The phrase 'automatically scrubbed' confirms PII removal, reducing sensitivity of returned data.
Attacks that exploit this kind of access
List user feedback entries. PII is automatically scrubbed from the response. It is categorised as a Read tool in the Pelaris MCP Server, which means it retrieves data without modifying state.
Register the Pelaris MCP server in PolicyLayer and add a rule for list_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 Pelaris. Nothing to install.
list_feedback 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 list_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 list_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.
list_feedback is provided by the Pelaris MCP server (thedonk/pelaris-mcp-server). 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 →