Apply an existing paragraph or scene revision after the user confirmed it. Use this for summary, viewpoint, tags, and body revisions without renumbering or renaming the file. Keep canon names as plain text instead of markdown links; the MCP layer refreshes plot and resume files after the update.
AI agents use update_paragraph 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 modifies existing paragraphs and scene content within a book repository (updates summaries, viewpoints, tags, and body text). These are Write-category operations: data is changed but the action is reversible — paragraphs can be revised again or reverted. It does not delete, execute arbitrary code, or trigger external side effects.
From the tool's definition Tool description states it 'Apply[s] an existing paragraph or scene revision' and 'Use this for summary, viewpoint, tags, and body revisions' — these are reversible modifications to content.
Attacks that exploit this kind of access
Apply an existing paragraph or scene revision after the user confirmed it. Use this for summary, viewpoint, tags, and body revisions without renumbering or renaming the file. Keep canon names as plain text instead of markdown links; the MCP layer refreshes plot and resume files after the update. 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 update_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.
update_paragraph 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 update_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 update_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.
update_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 →