Run an XCUITest in iosApp/iosAppUITests/iosAppUITests.swift
AI agents invoke remote_test_ios to trigger actions in Pistachio MCP Server. 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.
The tool explicitly runs tests (XCUITest) on an iOS application, which constitutes executing code/test suites on a device or simulator. This is an Execute category action as it triggers external operations (test execution) whose effects depend on the test content.
From the tool's definition Run an XCUITest in iosApp/iosAppUITests/iosAppUITests.swift
Attacks that exploit this kind of access
Run an XCUITest in iosApp/iosAppUITests/iosAppUITests.swift. It is categorised as a Execute tool in the Pistachio MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Pistachio MCP Server MCP server in PolicyLayer and add a rule for remote_test_ios: 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 Pistachio MCP Server. Nothing to install.
remote_test_ios 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 remote_test_ios 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 remote_test_ios. 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.
remote_test_ios is provided by the Pistachio MCP Server MCP server (jack-beanstalk-2022/pistachiomcp). 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 →