AI agents use dnd_end_snooze to create or update resources in Slack — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Slack environment.
This tool modifies user notification/availability status by ending snooze mode. It is a Write action because it changes user state reversibly—the user can re-enter snooze mode if needed. It is not Execute (no code/command triggered), not Destructive (no permanent data loss), not Financial, and not Read (causes a state change).
From the tool's definition Tool name 'dnd_end_snooze' and description 'End the current user's snooze mode' indicate modification of user status/notification settings. The action reverses a temporary do-not-disturb state, making it a reversible state change rather than data retrieval.
Attacks that exploit this kind of access
End the current user's snooze mode. It is categorised as a Write tool in the Slack MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Slack MCP server in PolicyLayer and add a rule for dnd_end_snooze: 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 Slack. Nothing to install.
dnd_end_snooze 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 dnd_end_snooze 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 dnd_end_snooze. 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.
dnd_end_snooze is provided by the Slack MCP server (karbassi/slack-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 →