Theme management: list, get, save, set active.\n\nActions:\n- list: List all themes and active theme names\n- get: Read a custom theme JSON (requires filename)\n- save: Create/update a custom theme (requires filename + theme)\n- set_active: Activate a theme (requires name)
AI agents use noteplan_themes to create or update resources in Noteplan — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Noteplan environment.
The tool primarily performs theme management with create/update and state-change capabilities. While 'list' and 'get' are read operations, the presence of 'save' (create/update) and 'set_active' (state modification) makes this a Write tool. It is not Destructive because theme changes are reversible; users can switch themes or delete custom themes.
From the tool's definition The tool description explicitly lists actions including 'save: Create/update a custom theme' and 'set_active: Activate a theme', which modify application state. These are reversible write operations.
Attacks that exploit this kind of access
Theme management: list, get, save, set active.\n\nActions:\n- list: List all themes and active theme names\n- get: Read a custom theme JSON (requires filename)\n- save: Create/update a custom theme (requires filename + theme)\n- set_active: Activate a theme (requires name). It is categorised as a Write tool in the Noteplan MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Noteplan MCP server in PolicyLayer and add a rule for noteplan_themes: 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_themes 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 noteplan_themes 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_themes. 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_themes 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 →