Uninstall your app from a workspace.
AI agents call apps_uninstall to permanently remove resources in Slack — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Uninstalling an app from a workspace removes all its permissions, bot tokens, and integrations. This action is not easily reversible (reinstallation would require going through the full installation flow again and may lose configuration/data), making it Destructive. The blast radius is high because it affects all users and workflows depending on that app in the workspace.
From the tool's definition 'Uninstall your app from a workspace' — removing an installed app is an irreversible action that eliminates the app's presence, permissions, and integrations from the workspace.
Attacks that exploit this kind of access
Uninstall your app from a workspace. It is categorised as a Destructive tool in the Slack MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Slack MCP server in PolicyLayer and add a rule for apps_uninstall: 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.
apps_uninstall 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 apps_uninstall 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 apps_uninstall. 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.
apps_uninstall 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 →