AI agents use add_layer 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/modifies the map state by adding geospatial data layers to the active data frame. It is reversible (layers can be removed), so it does not qualify as Destructive. While it controls ArcMap via arcpy, it is not executing arbitrary code or shell commands on behalf of the user—it is performing a specific, bounded map modification operation. Therefore, Write is the appropriate category.
From the tool's definition Adds a layer to the active data frame. The tool modifies the map composition by inserting new data, which is reversible (the layer can be removed). The description uses 'Añade una capa' (adds a layer) and references adding from shapefile/feature class paths.
Attacks that exploit this kind of access
Añade una capa al data frame activo desde una ruta a shapefile, feature class de. 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 add_layer: 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.
add_layer 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 add_layer 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 add_layer. 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.
add_layer 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 →