Animate a character with facial expressions and body movements from a reference performance video (Act-Two).
AI agents invoke character_performance to trigger actions in Apple Shortcuts. 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 an external animation process with side effects that depend on user-provided arguments (the reference performance video). While not destructive, write-capable, or financial, it fits Execute because it runs an external operation/service whose outcome is determined by the input parameters.
From the tool's definition Tool description states it will 'Animate a character with facial expressions and body movements from a reference performance video', which involves triggering an external operation (character animation) whose effects depend on the input video argument.
Documented attack patterns abuse exactly the kind of access character_performance gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Apple Shortcuts, and nothing reaches the server without passing your rules. This is the rule we recommend for character_performance:
{
"version": "1",
"default": "deny",
"tools": {
"character_performance": {
"limits": [
{
"counter": "character_performance_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}character_performance 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.
Animate a character with facial expressions and body movements from a reference performance video (Act-Two). It is categorised as a Execute tool in the Apple Shortcuts MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Apple Shortcuts MCP server in PolicyLayer and add a rule for character_performance: 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 Apple Shortcuts. Nothing to install.
character_performance 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 character_performance 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 character_performance. 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.
character_performance is provided by the Apple Shortcuts MCP server (@mindstone/mcp-server-apple-shortcuts). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Apple Shortcuts, 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.
423 Apple Shortcuts tools catalogued and risk-classified — across an index of 43,000+ MCP servers.