AI agents use zulip_add_reaction to create or update resources in Zulip MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Zulip MCP Server environment.
Adding a reaction modifies the message's metadata by appending a new reaction entry, but this is easily reversible (the reaction can be removed). This is characteristic of Write rather than Execute, as it does not trigger external operations or code execution. The severity is low because reactions have minimal impact on the Zulip workspace and can be trivially undone.
From the tool's definition Tool adds an emoji reaction to a message, which creates new data (the reaction) in a reversible manner. The description explicitly states 'Add an emoji reaction to a message', which is a write operation.
Documented attack patterns abuse exactly the kind of access zulip_add_reaction gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Zulip MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for zulip_add_reaction:
{
"version": "1",
"default": "deny",
"tools": {
"zulip_add_reaction": {
"limits": [
{
"counter": "zulip_add_reaction_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
} zulip_add_reaction stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Add an emoji reaction to a message. It is categorised as a Write tool in the Zulip MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Zulip MCP Server MCP server in PolicyLayer and add a rule for zulip_add_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 MCP Server. Nothing to install.
zulip_add_reaction is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the zulip_add_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 zulip_add_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.
zulip_add_reaction is provided by the Zulip MCP Server MCP server (monadical-sas/zulip-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Zulip MCP Server, 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.
8 Zulip MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.