bazel_ios_clean

THE RISK

Critical Risk

Why bazel_ios_clean needs a policy

The bazel_ios_clean tool, particularly with the expunge option, irreversibly deletes or removes data (build outputs and the entire output base). This matches the Destructive category definition: 'irreversibly deletes or overwrites data, or actions that cannot be undone.' While not as critical as deleting source code, losing build outputs can disrupt workflows and requires rebuilding.

From the tool's definition Tool name includes 'clean' and description explicitly states it 'Clean[s] Bazel build outputs' with option to 'expunge' and 'remove the entire output base.' These are irreversible operations that destroy build artifacts and cached data.

Risk signalsBulk/mass operation — affects multiple targets

Documented attack patterns abuse exactly the kind of access bazel_ios_clean gives an agent:

POLICY

How to control bazel_ios_clean

PolicyLayer is an MCP gateway — it sits between your AI agents and XcodeBazelMCP, and nothing reaches the server without passing your rules. This is the rule we recommend for bazel_ios_clean:

policy.json

{
  "version": "1",
  "default": "deny",
  "hide": [
    "bazel_ios_clean"
  ]
}

bazel_ios_clean disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.

Create a free account and register XcodeBazelMCP — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

RESTRICT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More XcodeBazelMCP tools

Destructive bazel_ios_agent_debug_log_clear Delete an agent debug NDJSON log file before a repro run (Cursor debug mode). Safe no-op i Destructive bazel_ios_erase_simulator Erase all content and settings from a simulator, restoring it to factory state. Destructive swift_package_clean Clean build artifacts of a Swift package ( Destructive bazel_ios_device_unpair Unpair a previously paired physical iOS device. Execute bazel_ios_agent_debug_repro One-shot Cursor debug repro: clear host log → build_and_run with AGENT_DEBUG_ launchEnv → Execute bazel_ios_lldb_breakpoint Set a breakpoint by file+line, symbol name, or delete/list breakpoints. Execute bazel_ios_privacy Grant, revoke, or reset privacy permissions for an app on a simulator. Execute bazel_daemon_start Start or ensure the per-workspace background daemon is running. The daemon keeps stateful

All 117 XcodeBazelMCP tools →

Destructive tools on other servers

Android Forensics ADB MCP Server create_full_backup 0xarchive web3_revoke_key Frida Game Hacking MCP clear_scan cPanel MCP Server clear_spam_box

Go deeper

Critical-risk tools in XcodeBazelMCP → Every critical-risk tool this server exposes, in one view.
All critical-risk MCP tools → Every critical-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Blast radius → How much damage one compromised or confused agent can do — and how to bound it.
Tool call approval → Approval gates on individual tool calls: auto-allow, prompt, or deny.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about bazel_ios_clean

What does the bazel_ios_clean tool do? +

Clean Bazel build outputs. Use expunge to remove the entire output base. It is categorised as a Destructive tool in the XcodeBazelMCP MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.

How do I enforce a policy on bazel_ios_clean? +

Register the XcodeBazel MCP server in PolicyLayer and add a rule for bazel_ios_clean: 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 XcodeBazelMCP. Nothing to install.

What risk level is bazel_ios_clean? +

bazel_ios_clean is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.

Can I rate-limit bazel_ios_clean? +

Yes. Add a rate_limit block to the bazel_ios_clean 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.

How do I block bazel_ios_clean completely? +

Set action: deny in the PolicyLayer policy for bazel_ios_clean. 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.

What MCP server provides bazel_ios_clean? +

bazel_ios_clean is provided by the XcodeBazel MCP server (xcodebazelmcp/xcodebazelmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every XcodeBazelMCP tool call.

Start from XcodeBazelMCP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →