flc_truncate
AI agents call flc_truncate to permanently remove resources in ArcGIS MCP — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Truncate operations irreversibly delete data in bulk and cannot be undone. Even though the description is empty, the semantic meaning of 'truncate' in data management contexts is unambiguous. This poses a critical blast radius—an AI agent could wipe an entire feature layer's data. Destructive category takes precedence over Write, Execute, or Read.
From the tool's definition Tool name 'flc_truncate' refers to truncating a feature layer collection, which irreversibly removes all records from a dataset. The term 'truncate' in database and GIS contexts means to delete all rows/features without recourse to undo.
Attacks that exploit this kind of access
flc_truncate. It is categorised as a Destructive tool in the ArcGIS MCP MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the ArcGIS MCP server in PolicyLayer and add a rule for flc_truncate: 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.
flc_truncate is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the flc_truncate 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 flc_truncate. 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.
flc_truncate 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 →