AI agents use dnd_set_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 preferences/status in Slack by enabling Do Not Disturb mode. It is reversible (the user can disable it), affects only the current user's notification settings, and has no destructive, financial, or code execution implications. It qualifies as Write because it creates/modifies data (user status) without irreversible consequences.
From the tool's definition Tool name 'dnd_set_snooze' and description 'Turn on Do Not Disturb mode for the current user' indicate modification of user status settings. This creates/updates a reversible state change (Do Not Disturb mode) for the authenticated user.
Attacks that exploit this kind of access
Turn on Do Not Disturb mode for the current user. 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_set_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_set_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_set_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_set_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_set_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 →