Remove a book from a list. Use id or list_id + book_id.
AI agents call remove_book_from_list to permanently remove resources in Hardcover — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Removing a book from a list is a destructive operation: it deletes the association between the book and the list. While not as catastrophic as dropping a database, it irreversibly removes the entry (the user would need to manually re-add it). The sibling tools include 'delete_list', 'delete_journal_entry', etc., suggesting this server treats removals as permanent deletions.
From the tool's definition 'Remove a book from a list' — removal is a deletion action that takes the book out of the list, which is not easily reversible without re-adding it manually.
Attacks that exploit this kind of access
Remove a book from a list. Use id or list_id + book_id. It is categorised as a Destructive tool in the Hardcover MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Hardcover MCP server in PolicyLayer and add a rule for remove_book_from_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.
remove_book_from_list is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the remove_book_from_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 remove_book_from_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.
remove_book_from_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 →