HUMAN CONFIRMATION: Confirm bulk deletion after reviewing preview. Requires explicit user choice from options provided.
AI agents call confirm_bulk_delete to permanently remove resources in Tally MCP — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Bulk deletion of forms is an irreversible operation that destroys data at scale. Even with human confirmation required, this remains a Destructive category tool. Severity is high because a single misuse could eliminate many forms, though the confirmation requirement prevents accidental triggering by an unaligned agent.
From the tool's definition Tool name contains 'bulk_delete' and description states it 'Confirm bulk deletion' — this irreversibly removes multiple forms. The requirement for 'explicit user choice' mitigates risk somewhat but does not change the destructive nature of the operation.
Documented attack patterns abuse exactly the kind of access confirm_bulk_delete gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Tally MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for confirm_bulk_delete:
{
"version": "1",
"default": "deny",
"hide": [
"confirm_bulk_delete"
]
} confirm_bulk_delete 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.
HUMAN CONFIRMATION: Confirm bulk deletion after reviewing preview. Requires explicit user choice from options provided. It is categorised as a Destructive tool in the Tally MCP MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Tally MCP server in PolicyLayer and add a rule for confirm_bulk_delete: 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 Tally MCP. Nothing to install.
confirm_bulk_delete 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 confirm_bulk_delete 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 confirm_bulk_delete. 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.
confirm_bulk_delete is provided by the Tally MCP server (learnwithcc/tally-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Tally MCP, 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.
18 Tally MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.