Delete a Slack message
AI agents call slack_delete_message to permanently remove resources in Slack MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Deleting a message permanently removes it from Slack, an action that cannot be undone. This is irreversible data destruction. While the blast radius is somewhat contained (affects one message, one workspace), the permanent nature of deletion and potential for misuse (e.g., deleting important communications, audit trails, or sensitive records shared in channels) warrants a 'high' severity rating.
From the tool's definition Tool name is 'slack_delete_message' with description 'Delete a Slack message'. The verb 'delete' indicates irreversible removal of data.
Attacks that exploit this kind of access
Delete a Slack message. It is categorised as a Destructive tool in the Slack MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Slack MCP Server MCP server in PolicyLayer and add a rule for slack_delete_message: 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 MCP Server. Nothing to install.
slack_delete_message 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 slack_delete_message 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 slack_delete_message. 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.
slack_delete_message is provided by the Slack MCP Server MCP server (sdancy10/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 →