AI agents call get_feedback_item 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 a single feedback entry from the Pelaris fitness coaching system. The action is purely read-based—it fetches data by identifier without creating, modifying, deleting, or executing external operations. The automated PII scrubbing further mitigates risk. Misuse would be limited to accessing fitness feedback data the AI agent is already authorized to view, presenting minimal blast radius.
From the tool's definition Tool name 'get_feedback_item' and description 'Get a single feedback entry by ID' indicates a retrieval operation with no side effects. The note that 'PII is automatically scrubbed' confirms data access without modification or deletion.
Attacks that exploit this kind of access
Get a single feedback entry by ID. PII is automatically scrubbed. 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 get_feedback_item: 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.
get_feedback_item 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_feedback_item 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_feedback_item. 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_feedback_item 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 →