item_related_items
AI agents call item_related_items to retrieve information from ArcGIS MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool name follows the 'get/retrieve' pattern typical of Read operations. However, confidence is moderate (0.6) because the description is empty, leaving some ambiguity about exact functionality and parameters. Without seeing the actual schema or parameters, it is possible (though unlikely) this could permit destructive operations if it accepts filters for deletion.
From the tool's definition Tool name 'item_related_items' suggests querying or retrieving related items associated with a parent item in ArcGIS. The absence of verbs like 'create', 'delete', 'update', or 'execute' in the name indicates a read-only retrieval operation.
Attacks that exploit this kind of access
item_related_items. It is categorised as a Read tool in the ArcGIS MCP MCP Server, which means it retrieves data without modifying state.
Register the ArcGIS MCP server in PolicyLayer and add a rule for item_related_items: 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_related_items is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the item_related_items 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_related_items. 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_related_items 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 →