Assemble the point-in-time context that should be read before writing or polishing a paragraph: prose defaults, scoped story-so-far context, prior scenes only, and the matching paragraph draft or final paragraph without leaking later story material. In prose, keep canon names as plain text instea...
AI agents call paragraph_writing_context 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 queries existing story context and paragraph information for reading purposes only. It assembles pre-existing data without creating, modifying, deleting, or executing any operations. The description explicitly focuses on providing context for human review before writing, which is fundamentally a read operation.
From the tool's definition The tool 'Assemble the point-in-time context that should be read before writing or polishing a paragraph' and mentions 'retrieves' story context, prose defaults, and prior scenes without modification. No creation, execution, or deletion of data is described.
Attacks that exploit this kind of access
Assemble the point-in-time context that should be read before writing or polishing a paragraph: prose defaults, scoped story-so-far context, prior scenes only, and the matching paragraph draft or final paragraph without leaking later story material. In prose, keep canon names as plain text instead of markdown links; the reader resolves visible mentions. 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 paragraph_writing_context: 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.
paragraph_writing_context 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 paragraph_writing_context 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 paragraph_writing_context. 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.
paragraph_writing_context 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 →