Assemble the full writing context needed to turn a scene script into polished prose. Returns: - The script body with meta-language beats - The script meta-language legend - The book writing-style guideline - The existing paragraph body if one already exists (revision mode) After calling this tool...
AI agents call script_to_paragraph to retrieve information from Narrarium without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and assembles contextual information (script body, legend, style guidelines, existing content) needed for writing. It is a read/fetch operation that gathers data to provide context, with no side effects of its own. The actual writing/modification happens in a subsequent step after calling this tool.
From the tool's definition Assemble the full writing context needed to turn a scene script into polished prose... Returns: The script body, meta-language legend, book writing-style guideline, existing paragraph body
Attacks that exploit this kind of access
Assemble the full writing context needed to turn a scene script into polished prose. Returns: - The script body with meta-language beats - The script meta-language legend - The book writing-style guideline - The existing paragraph body if one already exists (revision mode) After calling this tool, write the paragraph prose following the writing-style rules and the beat order in the script, then call \. It is categorised as a Read tool in the Narrarium MCP Server, which means it retrieves data without modifying state.
Register the Narrarium MCP server in PolicyLayer and add a rule for script_to_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.
script_to_paragraph is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the script_to_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 script_to_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.
script_to_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 →