bazel_ios_agent_debug_log_clear
Delete an agent debug NDJSON log file before a repro run (Cursor debug mode). Safe no-op if missing.
This record as markdown: /tools/xcodebazelmcp-xcodebazelmcp/bazel-ios-agent-debug-log-clear.md
What bazel_ios_agent_debug_log_clear does on XcodeBazelMCP
AI agents call bazel_ios_agent_debug_log_clear to permanently remove resources in XcodeBazelMCP, typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Why bazel_ios_agent_debug_log_clear is rated Critical
The tool deletes debug log files, which is an irreversible destructive operation. While the blast radius is limited (debug logs are typically non-critical artifacts and the tool is a 'safe no-op if missing'), file deletion is fundamentally a destructive action that cannot be undone. This justifies Destructive category over Write (which is reversible).
From the tool's definition Tool description explicitly states 'Delete an agent debug NDJSON log file' - the primary action is deletion of a file, which is irreversible.
Attacks that exploit this kind of access
The rule that runs bazel_ios_agent_debug_log_clear safely
PolicyLayer is an MCP gateway: it sits between your AI agents and XcodeBazelMCP, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For bazel_ios_agent_debug_log_clear, this is the rule to start with:
bazel_ios_agent_debug_log_clear is removed from the agent's tool list entirely, so the agent never calls it. The rest of the server keeps working.
The button opens the PolicyLayer dashboard: create your workspace, connect XcodeBazelMCP, apply this rule, and every bazel_ios_agent_debug_log_clear call is checked against it from then on.
Questions about bazel_ios_agent_debug_log_clear
Delete an agent debug NDJSON log file before a repro run (Cursor debug mode). Safe no-op if missing. 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.
Register the XcodeBazel MCP server in PolicyLayer and add a rule for bazel_ios_agent_debug_log_clear: 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.
bazel_ios_agent_debug_log_clear is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the bazel_ios_agent_debug_log_clear 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 bazel_ios_agent_debug_log_clear. 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.
bazel_ios_agent_debug_log_clear 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.
More on XcodeBazel, and thousands of servers like it.
Across the catalogue