List the table of contents (subtree) under a page.
AI agents call list_toc to retrieve information from Libretexts without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and presents hierarchical navigation data (table of contents) from LibreTexts. It has no capacity to modify, delete, execute operations, or create financial obligations. The operation is a pure query that returns existing structural metadata about the textbook content.
From the tool's definition Tool description states 'List the table of contents' which is a retrieval operation with no side effects. Paired with sibling tools 'get_page' and 'search' which are also read-only operations on a textbook library.
Attacks that exploit this kind of access
List the table of contents (subtree) under a page. It is categorised as a Read tool in the Libretexts MCP Server, which means it retrieves data without modifying state.
Register the Libretexts MCP server in PolicyLayer and add a rule for list_toc: 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 Libretexts. Nothing to install.
list_toc 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_toc 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_toc. 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_toc is provided by the Libretexts MCP server (mubashir1osmani/libretexts-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 →