AI agents invoke xcode_build_for_testing 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 code compilation and build artifact generation—external operations that modify the filesystem and consume system resources. While not destructive (artifacts can be cleaned), it is Execute-class because it runs a build system command whose effects are operationally significant and context-dependent.
From the tool's definition Tool invokes 'xcodebuild build-for-testing', which executes the Xcode build system to compile code and prepare test artifacts.
Attacks that exploit this kind of access
Build the project for testing (xcodebuild build-for-testing). 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 xcode_build_for_testing: 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.
xcode_build_for_testing 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 xcode_build_for_testing 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 xcode_build_for_testing. 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.
xcode_build_for_testing is provided by the Xcode MCP server (raunaksplanet/xcode-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →