Propose a revision for an existing final paragraph without writing files. Use this for targeted editorial passes like clarity, pacing, tension, dialogue, voice, show-dont-tell, or redundancy cleanup. Show the proposal to the user first, then apply it with update_paragraph only after clear confirm...
AI agents call revise_paragraph to permanently remove resources in Narrarium — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
An AI agent that decides to call revise_paragraph doesn't hesitate, doesn't double-check, and doesn't stop at one. Whatever it removes from Narrarium is gone — there is no undo for destructive operations.
Attacks that exploit this kind of access
Propose a revision for an existing final paragraph without writing files. Use this for targeted editorial passes like clarity, pacing, tension, dialogue, voice, show-dont-tell, or redundancy cleanup. Show the proposal to the user first, then apply it with update_paragraph only after clear confirmation. The result can also suggest state_changes to review if the paragraph carries continuity-sensitive beats. It is categorised as a Destructive tool in the Narrarium MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Narrarium MCP server in PolicyLayer and add a rule for revise_paragraph: 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.
revise_paragraph is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the revise_paragraph 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 revise_paragraph. 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.
revise_paragraph 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 →