AI agents call validate_book to retrieve information from Narrarium without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a read-only operation that queries the state of a local book repository to verify conformance with schema and structural rules. It has no side effects, creates no new data, modifies nothing, and triggers no external operations. The blast radius of misuse is minimal - a malicious agent could learn about repository structure but cannot harm data or systems.
From the tool's definition Tool performs validation of frontmatter and file placement rules - it checks/inspects existing data without modifying, creating, or deleting anything. The verb 'validate' indicates inspection and reporting of compliance status.
Attacks that exploit this kind of access
Validate Narrarium frontmatter and file placement rules inside the local book repository. It is categorised as a Read tool in the Narrarium MCP Server, which means it retrieves data without modifying state.
Register the Narrarium MCP server in PolicyLayer and add a rule for validate_book: 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 Narrarium. Nothing to install.
validate_book 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 validate_book 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 validate_book. 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.
validate_book is provided by the Narrarium MCP server (narrarium-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 →