item_export
AI agents use item_export to create or update resources in ArcGIS MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your ArcGIS MCP environment.
The tool name suggests exporting ArcGIS items (maps, layers, datasets) to an external format or location. This is a data transformation/creation action (Write category) rather than a simple read. The severity is medium because exported data could contain sensitive geographic or organizational information, and uncontrolled exports could enable data exfiltration.
From the tool's definition Tool name 'item_export' with empty description. In ArcGIS context, 'export' typically creates a new artifact (exported data, file, or copy) rather than modifying existing items. However, the empty description prevents certain classification.
Attacks that exploit this kind of access
item_export. It is categorised as a Write tool in the ArcGIS MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the ArcGIS MCP server in PolicyLayer and add a rule for item_export: 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 ArcGIS MCP. Nothing to install.
item_export 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 item_export 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 item_export. 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.
item_export is provided by the ArcGIS MCP server (renemorenow/arcgis-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 →