Pushes the current directory onto a stack and changes to a new directory.
AI agents invoke push_directory to trigger actions in Xcode. 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 changes the working directory of the process, which is an operational side effect that influences subsequent commands and tool invocations. It is not simply reading data; it modifies execution context. Misuse could redirect file operations to unintended locations, affecting builds or file modifications.
From the tool's definition Pushes the current directory onto a stack and changes to a new directory
Documented attack patterns abuse exactly the kind of access push_directory gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Xcode, and nothing reaches the server without passing your rules. This is the rule we recommend for push_directory:
{
"version": "1",
"default": "deny",
"tools": {
"push_directory": {
"limits": [
{
"counter": "push_directory_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
} push_directory 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.
Pushes the current directory onto a stack and changes to a new directory. It is categorised as a Execute tool in the Xcode MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Xcode MCP server in PolicyLayer and add a rule for push_directory: 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 Xcode. Nothing to install.
push_directory 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 push_directory 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 push_directory. 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.
push_directory is provided by the Xcode MCP server (xcode-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 69 Xcode tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
69 Xcode tools catalogued and risk-classified — across an index of 42,500+ MCP servers.