AI agents use create_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 performs a create operation on user data (a list in the Hardcover library system). Creation is inherently reversible through deletion (evidenced by the sibling tool 'delete_list'), making it Write rather than Destructive. The severity is medium because misuse could clutter a user's library with unwanted lists, but the impact is limited in scope and easily remedied.
From the tool's definition The tool "create_list" creates a new Hardcover list, which is a reversible data modification operation. The description states it creates a new list, fitting the Write category definition of 'creates or modifies data reversibly'.
Attacks that exploit this kind of access
Create a new 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 create_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.
create_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 create_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 create_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.
create_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 →