Compute objective text metrics and style context for a single paragraph and return them as structured data so the LLM can perform the editorial reading before calling write_paragraph_evaluation. Call this first, read the result carefully, then call write_paragraph_evaluation with your editorial j...
AI agents call prepare_paragraph_evaluation 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 performs data retrieval and analysis only—it computes and returns metrics without modifying, deleting, or executing operations. It is a preparatory read operation that gathers information for subsequent editorial judgment by the LLM.
From the tool's definition The tool 'compute[s] objective text metrics and style context' and 'return[s] them as structured data' for analysis. The description explicitly states to 'read the result carefully' before any write operation.
Attacks that exploit this kind of access
Compute objective text metrics and style context for a single paragraph and return them as structured data so the LLM can perform the editorial reading before calling write_paragraph_evaluation. Call this first, read the result carefully, then call write_paragraph_evaluation with your editorial judgment. 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 prepare_paragraph_evaluation: 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.
prepare_paragraph_evaluation 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 prepare_paragraph_evaluation 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 prepare_paragraph_evaluation. 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.
prepare_paragraph_evaluation 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 →