Send a message to a specific stream and topic (fire-and-forget).
AI agents use send_message to create or update resources in Zulip — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Zulip environment.
This tool creates persistent, reversible data (messages can be edited or deleted by other means). It does not execute code, delete data, or move money. The severity is medium because widespread message spam or injected misinformation could disrupt a Zulip workspace, but the impact is bounded to communication channels and reversible.
From the tool's definition Tool description states 'Send a message to a specific stream and topic' — this creates new data (a message) in the Zulip instance. The 'fire-and-forget' nature confirms it is a write operation with no retrieval or execution of external code.
Documented attack patterns abuse exactly the kind of access send_message 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 send_message:
{
"version": "1",
"default": "deny",
"tools": {
"send_message": {
"limits": [
{
"counter": "send_message_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}send_message 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.
Send a message to a specific stream and topic (fire-and-forget). It is categorised as a Write tool in the Zulip MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Zulip MCP server in PolicyLayer and add a rule for send_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 Zulip. Nothing to install.
send_message 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 send_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 send_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.
send_message 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.