Search locations, manage guides, save favorites, and get directions using Apple Maps
AI agents invoke maps to trigger actions in Apple 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 spans multiple categories: 'Search locations' and 'get directions' are Read operations, but 'manage guides' and 'save favorites' involve Write operations (creating/modifying persistent data in Apple Maps). Since Write is more severe than Read, and the tool can modify saved data in Apple Maps, Write would normally apply. However, 'manage guides' could also involve deletion of guides, which is ambiguous.
From the tool's definition Search locations, manage guides, save favorites, and get directions using Apple Maps
Documented attack patterns abuse exactly the kind of access maps gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Apple MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for maps:
{
"version": "1",
"default": "deny",
"tools": {
"maps": {
"limits": [
{
"counter": "maps_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}maps 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.
Search locations, manage guides, save favorites, and get directions using Apple Maps. It is categorised as a Execute tool in the Apple MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Apple MCP server in PolicyLayer and add a rule for maps: 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 MCP. Nothing to install.
maps 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 maps 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 maps. 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.
maps is provided by the Apple MCP server (jxnl/apple-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Apple 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.
8 Apple MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.