Get the main summary for a book
AI agents call get_book_summary to retrieve information from LibraLM MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a simple data retrieval operation that queries pre-generated book summaries. It has no capability to modify, delete, execute code, or affect any external systems. The tool merely returns existing summarized content from a fixed database of 50+ book summaries.
From the tool's definition Tool retrieves a book summary with no side effects. Description states 'Get the main summary for a book' and server provides 'access to...book summaries and chapter breakdowns' with capabilities to 'search books' and 'get instant access to key insights.' All…
Attacks that exploit this kind of access
Get the main summary for a book. It is categorised as a Read tool in the LibraLM MCP Server MCP Server, which means it retrieves data without modifying state.
Register the LibraLM MCP Server MCP server in PolicyLayer and add a rule for get_book_summary: 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 LibraLM MCP Server. Nothing to install.
get_book_summary 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_book_summary 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_book_summary. 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_book_summary is provided by the LibraLM MCP Server MCP server (libralm-ai/libralm_mcp_server). 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 →