Refresh the total book evaluation with chapter scorecards, writing-style-aware editorial checks, canon coherence checks, weighted verdict summaries, explicit verdict explanations, and revision priorities, and optionally refresh all chapter and paragraph evaluations too.
AI agents use evaluate_book to create or update resources in Narrarium — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Narrarium environment.
The tool refreshes and updates evaluation records (scorecards, verdicts, summaries) stored in the book repository. This is a Write operation as it modifies/overwrites existing evaluation data. It does not delete content irreversibly, execute code, or involve financial transactions. Severity is medium because misuse could overwrite carefully maintained editorial evaluations across an entire book project.
From the tool's definition 'Refresh the total book evaluation' and 'optionally refresh all chapter and paragraph evaluations too' — this updates/overwrites stored evaluation data
Attacks that exploit this kind of access
Refresh the total book evaluation with chapter scorecards, writing-style-aware editorial checks, canon coherence checks, weighted verdict summaries, explicit verdict explanations, and revision priorities, and optionally refresh all chapter and paragraph evaluations too. It is categorised as a Write tool in the Narrarium MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Narrarium MCP server in PolicyLayer and add a rule for evaluate_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.
evaluate_book is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the evaluate_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 evaluate_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.
evaluate_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 →