AI agents call slack_reactions_remove to permanently remove resources in Sage MCP — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Removing a reaction is a deletion operation that cannot be trivially undone (the original reaction state is lost). While the blast radius is limited — only an emoji reaction is deleted, not a message or channel — it is still an irreversible removal of existing data, placing it in the Destructive category at medium severity.
From the tool's definition 'Remove an emoji reaction from a message' — the word 'remove' indicates deletion of existing data (the reaction)
Documented attack patterns abuse exactly the kind of access slack_reactions_remove gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Sage MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for slack_reactions_remove:
{
"version": "1",
"default": "deny",
"hide": [
"slack_reactions_remove"
]
}slack_reactions_remove 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.
Remove an emoji reaction from a message. It is categorised as a Destructive tool in the Sage MCP MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Sage MCP server in PolicyLayer and add a rule for slack_reactions_remove: 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 Sage MCP. Nothing to install.
slack_reactions_remove 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_reactions_remove 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_reactions_remove. 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_reactions_remove is provided by the Sage MCP server (sagemcp/sagemcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 359 Sage MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
359 Sage MCP tools catalogued and risk-classified — across an index of 42,500+ MCP servers.