AI agents call remove_reaction to permanently remove resources in Zulip — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Removing a reaction deletes existing data (the emoji reaction) and cannot be trivially undone without the original actor re-adding it. While the blast radius is low (only cosmetic emoji reactions are affected), the action is a deletion of existing state. Severity is low because reactions are minor metadata with minimal real-world impact.
From the tool's definition Remove an emoji reaction from a message
Documented attack patterns abuse exactly the kind of access remove_reaction gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Zulip, and nothing reaches the server without passing your rules. This is the rule we recommend for remove_reaction:
{
"version": "1",
"default": "deny",
"hide": [
"remove_reaction"
]
}remove_reaction 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 Zulip MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Zulip MCP server in PolicyLayer and add a rule for remove_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 Zulip. Nothing to install.
remove_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 remove_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 remove_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.
remove_reaction is provided by the Zulip MCP server (windborne/zulipmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Zulip, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
27 Zulip tools catalogued and risk-classified — across an index of 43,000+ MCP servers.