AI agents use add_book_to_list 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.
This tool creates or modifies a list by adding a book to it. This is a write operation that changes user data (list contents) but is reversible and has no side effects beyond the user's own library management. No code execution, data destruction, or financial impact is involved. Severity is low because the blast radius of misuse is confined to the user's own lists with no external consequences.
From the tool's definition Tool name 'add_book_to_list' and description 'Add a book to a Hardcover list' indicate creation/modification of list membership data. The action is reversible (books can be removed via delete_list or by removing items).
Attacks that exploit this kind of access
Add a book to a Hardcover list. 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 add_book_to_list: 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.
add_book_to_list 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 add_book_to_list 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 add_book_to_list. 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.
add_book_to_list 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 →