AI agents call get_passage 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 queries and returns existing ebook content from the local semantic library. It performs a read-only retrieval operation analogous to fetching or getting data. There is no indication of data modification, deletion, execution of code, or financial impact. The blast radius of misuse is minimal — an agent could retrieve irrelevant or sensitive passages, but cannot alter the library or trigger external effects.
From the tool's definition Tool description states 'Retrieve the full stored text for a given book and chapter' — retrieves data with no modification or side effects.
Attacks that exploit this kind of access
Retrieve the full stored text for a given book and chapter. 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 get_passage: 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.
get_passage 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 get_passage 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 get_passage. 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.
get_passage 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 →