Add or remove an emoji reaction.
AI agents call toggle_reaction to permanently remove resources in ZulipChat MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
An AI agent that decides to call toggle_reaction doesn't hesitate, doesn't double-check, and doesn't stop at one. Whatever it removes from ZulipChat MCP Server is gone — there is no undo for destructive operations.
Attacks that exploit this kind of access
Add or remove an emoji reaction. It is categorised as a Destructive tool in the ZulipChat MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the ZulipChat MCP Server MCP server in PolicyLayer and add a rule for toggle_reaction: 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 ZulipChat MCP Server. Nothing to install.
toggle_reaction 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 toggle_reaction 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 toggle_reaction. 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.
toggle_reaction is provided by the ZulipChat MCP Server MCP server (pypi:zulipchat-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.