AI agents call list_books to retrieve information from Scholar without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a straightforward read operation—listing books and their chapter counts from an existing index. It retrieves information without creating, modifying, deleting, or executing any operations. The action is inherently passive and has no destructive or side-effect potential, making it a low-severity Read operation.
From the tool's definition Tool name 'list_books' and description 'List all books in the index with chapter counts' indicate a retrieval operation that queries metadata about indexed books without modification or side effects.
Attacks that exploit this kind of access
List all books in the index with chapter counts. It is categorised as a Read tool in the Scholar MCP Server, which means it retrieves data without modifying state.
Register the Scholar MCP server in PolicyLayer and add a rule for list_books: 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 Scholar. Nothing to install.
list_books is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the list_books 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 list_books. 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.
list_books is provided by the Scholar MCP server (unlomtrois/little-librarian). 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 →