Refresh a full chapter evaluation by reading the whole chapter across all paragraph files, combining objective text signals with editorial reading against the active writing-style files and canon coherence checks, then writing objective/editorial scores, a weighted verdict, an explanation of why ...
AI agents use evaluate_chapter 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 reads chapter content but its primary function is to generate and write evaluation outputs (scores, verdicts, explanations, paragraph evaluation files). This is a reversible modification operation that creates or updates evaluation artifacts rather than destructively deleting data or irreversibly changing source content. The 'refresh' operation and file writing constitute Write-category activity.
From the tool's definition Tool description states it performs 'writing objective/editorial scores', 'weighted verdict', 'explanation', and 'next steps plus paragraph evaluation files' — all indicating creation or modification of evaluation documents and metadata files.
Attacks that exploit this kind of access
Refresh a full chapter evaluation by reading the whole chapter across all paragraph files, combining objective text signals with editorial reading against the active writing-style files and canon coherence checks, then writing objective/editorial scores, a weighted verdict, an explanation of why that verdict landed there, and next steps plus paragraph evaluation files. 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_chapter: 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_chapter 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_chapter 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_chapter. 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_chapter 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 →