AI agents invoke broadcast-event to trigger actions in Liveblocks. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
Broadcasting an event triggers external operations in a Liveblocks room, potentially affecting all connected clients in real-time. This is an Execute-category action because it dispatches an event whose effects depend on the arguments and what listeners do in response. The blast radius is high since a malicious or erroneous broadcast could disrupt all active users in a room.
From the tool's definition Broadcast an event to a Liveblocks room
Documented attack patterns abuse exactly the kind of access broadcast-event gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Liveblocks, and nothing reaches the server without passing your rules. This is the rule we recommend for broadcast-event:
{
"version": "1",
"default": "deny",
"tools": {
"broadcast-event": {
"limits": [
{
"counter": "broadcast-event_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}broadcast-event stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Broadcast an event to a Liveblocks room. It is categorised as a Execute tool in the Liveblocks MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Liveblocks MCP server in PolicyLayer and add a rule for broadcast-event: 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 Liveblocks. Nothing to install.
broadcast-event is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the broadcast-event 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 broadcast-event. 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.
broadcast-event is provided by the Liveblocks MCP server (liveblocks/liveblocks-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Liveblocks, 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.
39 Liveblocks tools catalogued and risk-classified — across an index of 43,000+ MCP servers.