Remove an option from a Local or Global OptionSet (Dataverse DeleteOptionValue action). WARNING: existing records that hold this integer value are NOT updated and will retain the now-orphan number — warn the user before deleting.
AI agents call delete_picklist_option to permanently remove resources in Dataverse — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool permanently removes an OptionSet value from the schema, which cannot be undone. While individual records are not deleted, the action is irreversible and creates orphaned data references in existing records—a destructive side effect. This is more severe than Write (reversible modification) and clearly falls under Destructive category.
From the tool's definition 'Remove an option from a Local or Global OptionSet' and 'existing records that hold this integer value are NOT updated and will retain the now-orphan number' indicate irreversible deletion with data integrity consequences
Documented attack patterns abuse exactly the kind of access delete_picklist_option gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Dataverse, and nothing reaches the server without passing your rules. This is the rule we recommend for delete_picklist_option:
{
"version": "1",
"default": "deny",
"hide": [
"delete_picklist_option"
]
}delete_picklist_option disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.
Free to start. No card required.
Remove an option from a Local or Global OptionSet (Dataverse DeleteOptionValue action). WARNING: existing records that hold this integer value are NOT updated and will retain the now-orphan number — warn the user before deleting. It is categorised as a Destructive tool in the Dataverse MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Dataverse MCP server in PolicyLayer and add a rule for delete_picklist_option: 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 Dataverse. Nothing to install.
delete_picklist_option 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 delete_picklist_option 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 delete_picklist_option. 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.
delete_picklist_option is provided by the Dataverse MCP server (rededis/dataverse-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Dataverse, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
22 Dataverse tools catalogued and risk-classified — across an index of 43,000+ MCP servers.