AI agents use create_paragraph_draft 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 new draft content within a version-controlled drafts directory, which is a reversible write operation. It does not execute arbitrary code, delete data permanently, or move financial resources. The severity is medium because drafts are working materials, but miscreation could still require cleanup effort and impact the writing workflow.
From the tool's definition Tool description states it will 'Create a rough paragraph or scene draft' - the verb 'Create' indicates data creation. The draft exists in a drafts/ directory, separate from final chapters, making modifications reversible.
Attacks that exploit this kind of access
Create a rough paragraph or scene draft inside drafts/ using the same chapter tree as the final chapter. 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 create_paragraph_draft: 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.
create_paragraph_draft 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 create_paragraph_draft 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 create_paragraph_draft. 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.
create_paragraph_draft 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 →