AI agents use set_user_book to create or update resources in Hardcover — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Hardcover environment.
The tool creates or modifies user book records in the Hardcover library—a reversible operation. It changes reading lists or book metadata but does not permanently delete data (unlike delete_user_book) or execute external commands. The blast radius is limited to the user's personal library state, making it Write severity rather than higher categories.
From the tool's definition Tool description 'Set a book' combined with server context describing 'reading status updates' and the presence of related tools like 'add_user_book_read' and 'delete_user_book' indicates this modifies user library state.
Attacks that exploit this kind of access
Set a book. It is categorised as a Write tool in the Hardcover MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Hardcover MCP server in PolicyLayer and add a rule for set_user_book: 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.
set_user_book 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 set_user_book 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 set_user_book. 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.
set_user_book 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 →