Send a poke (alert notification) to a client - more attention-grabbing than a private message
AI agents use poke_client to create or update resources in TeamSpeak MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your TeamSpeak MCP environment.
Poking a client is a non-destructive, reversible action that sends a notification/alert. It creates a temporary communication event but does not create permanent data modifications, delete anything, execute code, or involve financial transactions. This is clearly a Write action (creating a transient notification) rather than Execute or Destructive.
From the tool's definition Tool sends a 'poke (alert notification) to a client' - a reversible communication action that modifies communication state but does not alter persistent data, delete resources, or execute arbitrary operations.
Documented attack patterns abuse exactly the kind of access poke_client gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and TeamSpeak MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for poke_client:
{
"version": "1",
"default": "deny",
"tools": {
"poke_client": {
"limits": [
{
"counter": "poke_client_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}poke_client 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 poke (alert notification) to a client - more attention-grabbing than a private message. It is categorised as a Write tool in the TeamSpeak MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the TeamSpeak MCP server in PolicyLayer and add a rule for poke_client: 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 TeamSpeak MCP. Nothing to install.
poke_client 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 poke_client 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 poke_client. 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.
poke_client is provided by the TeamSpeak MCP server (marlburrow/teamspeak-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from TeamSpeak MCP, 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.
40 TeamSpeak MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.