AI agents call get_user_reviews to retrieve information from Hardcover without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays user review data without creating, modifying, or deleting any information. It is a straightforward read operation that queries existing reviews, ratings, and associated book information. No side effects or state changes occur. Severity is low because the blast radius of misuse is limited to information disclosure of the user's own review history.
From the tool's definition Tool name 'get_user_reviews' and description 'List your reviews' indicate retrieval of existing data with no modification capability. The verb 'List' and the scope 'your reviews' (read-only access to user's own review data) confirm this is a query operation.
Attacks that exploit this kind of access
List your reviews, newest first. Includes review text, rating, and book info. It is categorised as a Read tool in the Hardcover MCP Server, which means it retrieves data without modifying state.
Register the Hardcover MCP server in PolicyLayer and add a rule for get_user_reviews: 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 Hardcover. Nothing to install.
get_user_reviews 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_user_reviews 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_user_reviews. 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_user_reviews is provided by the Hardcover MCP server (kristianedlund/hardcover-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 →