AI agents use set_active_df 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 modifies the active state of the ArcMap session by changing which data frame is active and triggering a refresh. It is a reversible state change (you can switch back), so it falls under Write rather than Execute or Destructive. Misuse could disrupt ongoing GIS workflows but does not delete data or run arbitrary code.
From the tool's definition 'Fija el data frame activo por nombre y refresca' — sets (fixes/changes) the active data frame by name and refreshes the session state
Attacks that exploit this kind of access
Fija el data frame activo por nombre y refresca. Las tools que operan sobre 'el df. 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 set_active_df: 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.
set_active_df 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 set_active_df 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 set_active_df. 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.
set_active_df 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 →