AI agents call get_directions to retrieve information from Python Apple MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries map data to retrieve directions—a read-only operation with no state changes. While it interacts with macOS applications via AppleScript, it only retrieves navigation information. The broader server context shows other tools like create_event, create_note, and create_reminder which are clearly Write operations, while search_* tools are Read.
From the tool's definition The tool description states "Get directions between two locations" with no mention of modifying data, executing commands, or triggering side effects. It retrieves directional information from the Maps application.
Documented attack patterns abuse exactly the kind of access get_directions gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Python Apple MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for get_directions:
{
"version": "1",
"default": "deny",
"tools": {
"get_directions": {}
}
}get_directions is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Get directions between two locations. It is categorised as a Read tool in the Python Apple MCP MCP Server, which means it retrieves data without modifying state.
Register the Python Apple MCP server in PolicyLayer and add a rule for get_directions: 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 Python Apple MCP. Nothing to install.
get_directions is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_directions 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 get_directions. 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.
get_directions is provided by the Python Apple MCP server (jxnl/python-apple-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Python 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.
13 Python Apple MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.