AI agents use export_icon_to_pdf to create or update resources in Nucleo — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Nucleo environment.
This tool creates or writes a new file to disk (PDF export), which is a reversible modification. The blast radius is minimal—at worst, it creates unwanted files on the local filesystem, which can be deleted. There is no data destruction, financial impact, or code execution involved. The operation is write-class because it generates new output at a user-specified location.
From the tool's definition Tool performs 'Export a Nucleo icon to a PDF file at the specified path', which creates a new file (PDF) on the filesystem based on icon data.
Attacks that exploit this kind of access
Export a Nucleo icon to a PDF file at the specified path. It is categorised as a Write tool in the Nucleo MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Nucleo MCP server in PolicyLayer and add a rule for export_icon_to_pdf: 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 Nucleo. Nothing to install.
export_icon_to_pdf 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 export_icon_to_pdf 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 export_icon_to_pdf. 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.
export_icon_to_pdf is provided by the Nucleo MCP server (julianallchin/nucleo-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 →