Close the speech UI window. This will gracefully shut down the speech UI window if it's currently running. Use this when you're done with voice interaction to clean up resources. Returns: A message indicating whether the UI was successfully closed.
AI agents invoke close_ui to trigger actions in Speech MCP. 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.
This tool triggers an external operation (closing a UI window and cleaning up resources). It's not purely reading data, nor writing/modifying persistent data. It executes an action against a running process. The blast radius is low since it only closes a UI window with no destructive or financial implications.
From the tool's definition Close the speech UI window... gracefully shut down the speech UI window... clean up resources
Documented attack patterns abuse exactly the kind of access close_ui gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Speech MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for close_ui:
{
"version": "1",
"default": "deny",
"tools": {
"close_ui": {
"limits": [
{
"counter": "close_ui_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}close_ui 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.
Close the speech UI window. This will gracefully shut down the speech UI window if it's currently running. Use this when you're done with voice interaction to clean up resources. Returns: A message indicating whether the UI was successfully closed. It is categorised as a Execute tool in the Speech MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Speech MCP server in PolicyLayer and add a rule for close_ui: 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 Speech MCP. Nothing to install.
close_ui 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 close_ui 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 close_ui. 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.
close_ui is provided by the Speech MCP server (kvadratni/speech-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Speech 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.
7 Speech MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.