AI agents use export_pdf to create or update resources in Arcmap — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Arcmap environment.
This tool creates a new file (PDF) based on the current map layout. It is Write category because it creates/generates new data (a PDF export) reversibly—the PDF can be deleted or overwritten. It does not execute arbitrary code or delete data, so it does not rise to Execute or Destructive.
From the tool's definition Tool exports/saves the current ArcMap layout to a PDF file at the specified output path (`salida`). The description explicitly states 'Exporta el layout actual de ArcMap a un PDF' (Exports the current ArcMap layout to a PDF).
Attacks that exploit this kind of access
Exporta el layout actual de ArcMap a un PDF en la ruta salida. It is categorised as a Write tool in the Arcmap MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Arcmap MCP server in PolicyLayer and add a rule for export_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 Arcmap. Nothing to install.
export_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_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_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_pdf is provided by the Arcmap MCP server (pedralcg/arcmap-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 →