AI agents invoke xcode_run_tests 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.
Running tests via xcodebuild executes arbitrary test code whose behavior depends on the test suite contents and project configuration. While tests are typically intended to be safe, an AI agent could be manipulated to run malicious test code, access sensitive data during test execution, or trigger unintended side effects.
From the tool's definition Tool runs tests using xcodebuild, which executes code. The description explicitly states 'Run tests' and invokes xcodebuild, a command-line tool that compiles and executes test targets. Test execution is inherently an Execute action.
Attacks that exploit this kind of access
Run tests using xcodebuild. 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_run_tests: 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_run_tests 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_run_tests 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_run_tests. 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_run_tests 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 →