AI agents invoke clean_swift_package 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 triggers an external operation (Swift Package Manager's clean command) whose effects are predictable but involve modifying the filesystem by removing build artifacts. It is Execute rather than Write because it runs a command/tool rather than directly manipulating tracked project files, and it is not Destructive because cleaning build artifacts is reversible (rebuilding will regenerate them).
From the tool's definition Tool name is 'clean_swift_package' and description states it 'Cleans the build artifacts of a Swift Package.' The action of cleaning build artifacts involves executing a build system command (typically `swift package clean` or equivalent) that removes…
Documented attack patterns abuse exactly the kind of access clean_swift_package 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 clean_swift_package:
{
"version": "1",
"default": "deny",
"tools": {
"clean_swift_package": {
"limits": [
{
"counter": "clean_swift_package_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}clean_swift_package 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.
Cleans the build artifacts of a Swift Package. 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 clean_swift_package: 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.
clean_swift_package 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 clean_swift_package 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 clean_swift_package. 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.
clean_swift_package 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.