Task lifecycle and paragraph inspection.\n\nParagraph actions:\n- get: Get note lines with metadata (requires note ref). Returns lineIndex, content, type. Filter with types param: base types (title, heading, bullet, text, quote, separator, empty), task/checklist by status (open-task, done-task, c...
AI agents call noteplan_paragraphs to retrieve information from Noteplan without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool exclusively retrieves and inspects data (paragraphs, task metadata, line content) from existing notes without modifying, deleting, or executing operations. It is a read-only query interface with no side effects. The low severity reflects that unauthorized access to note content carries minimal blast radius compared to destructive or financial operations.
From the tool's definition Tool description states 'get: Get note lines with metadata' and 'Returns lineIndex, content, type. Filter with types param'. The only action described is retrieval of paragraph/line data from notes with optional filtering.
Attacks that exploit this kind of access
Task lifecycle and paragraph inspection.\n\nParagraph actions:\n- get: Get note lines with metadata (requires note ref). Returns lineIndex, content, type. Filter with types param: base types (title, heading, bullet, text, quote, separator, empty), task/checklist by status (open-task, done-task, cancelled-task, scheduled-task, open-checklist, done-checklist, etc). types=[. It is categorised as a Read tool in the Noteplan MCP Server, which means it retrieves data without modifying state.
Register the Noteplan MCP server in PolicyLayer and add a rule for noteplan_paragraphs: 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 Noteplan. Nothing to install.
noteplan_paragraphs 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 noteplan_paragraphs 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 noteplan_paragraphs. 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.
noteplan_paragraphs is provided by the Noteplan MCP server (@noteplanco/noteplan-mcp). 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 →