AI agents use set_edition_owned 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 data (ownership state) but does so reversibly—a user can change the ownership status at any time. This is a metadata update operation with no destructive, financial, or code-execution aspects. It falls squarely in the Write category with low severity due to limited blast radius (only affects one user's library metadata).
From the tool's definition Tool name is 'set_edition_owned' and description states 'Mark an edition as owned or not owned.' This modifies the ownership status of a book edition in the user's library.
Attacks that exploit this kind of access
Mark an edition as owned or not owned. 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_edition_owned: 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_edition_owned 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_edition_owned 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_edition_owned. 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_edition_owned 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 →