Stop a running slideshow
AI agents invoke keynote_stop_slideshow to trigger actions in Iwork. 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 executes a command to stop a running slideshow, which is an external operation with side effects (state change in the Keynote application). While the blast radius is minimal—stopping a slideshow is non-destructive and non-financial—it still constitutes an Execute action because it triggers application behavior based on invocation.
From the tool's definition Tool name 'keynote_stop_slideshow' and description 'Stop a running slideshow' indicate an action that triggers an external operation (halting an active Keynote slideshow process).
Documented attack patterns abuse exactly the kind of access keynote_stop_slideshow gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Iwork, and nothing reaches the server without passing your rules. This is the rule we recommend for keynote_stop_slideshow:
{
"version": "1",
"default": "deny",
"tools": {
"keynote_stop_slideshow": {
"limits": [
{
"counter": "keynote_stop_slideshow_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
} keynote_stop_slideshow 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.
Stop a running slideshow. It is categorised as a Execute tool in the Iwork MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Iwork MCP server in PolicyLayer and add a rule for keynote_stop_slideshow: 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 Iwork. Nothing to install.
keynote_stop_slideshow 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 keynote_stop_slideshow 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 keynote_stop_slideshow. 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.
keynote_stop_slideshow is provided by the Iwork MCP server (reichenbach/iwork_mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Iwork, 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.
114 Iwork tools catalogued and risk-classified — across an index of 43,000+ MCP servers.