AI agents use export_epub 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.
This tool creates and writes a new file output (EPUB format) derived from existing book repository data. It is a Write operation because it generates/creates new data in a standard file format, reversible through deletion or re-export. It does not execute arbitrary code, delete data irreversibly, or involve financial transactions.
From the tool's definition Tool description states it exports book repository content into an EPUB file, which creates a new file artifact based on existing markdown content.
Attacks that exploit this kind of access
Export the current book repository into an EPUB file from the ordered chapter and paragraph markdown 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 export_epub: 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.
export_epub 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 export_epub 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 export_epub. 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.
export_epub 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 →