// SCAN REPORT

Sl Test

29 tools. 22 can modify or destroy data without limits.

3 destructive tools with no built-in limits. Policy required.

Last updated: 1 Jul 2026

22 can modify or destroy data

7 read-only

29 tools total

Community server · catalogue entry verified 01/07/2026

How to control Sl Test ↓

TOOL MAP

What Sl Test exposes to your agents

Read (7) Write / Execute (19) Destructive / Financial (3)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Sl Test tools

Destructive · Medium reset_simulator_location A reset operation generally destroys current state (location data, simulator configuration) and returns the device to a default state, which is not easily reversible without reconfiguration. Destructive · High clean_proj 'Cleaning build products' irreversibly deletes compiled artifacts, derived data, and build outputs for an Xcode project. Destructive · High clean_ws Cleaning build products irreversibly deletes compiled artifacts, derived data, and build outputs. Execute · Medium reset_network_condition This tool modifies the runtime state of a simulator by resetting its network conditions.

22 of Sl Test's 29 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Sl Test

PolicyLayer is an MCP gateway — it sits between your AI agents and Sl Test, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations

{
  "clean_proj": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "set_sim_appearance": {
    "limits": [
      {
        "counter": "set_sim_appearance_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "describe_ui": {
    "limits": [
      {
        "counter": "describe_ui_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Sl Test — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON SL TEST →

Instant setup, no code required.

FULL CATALOGUE

All 29 Sl Test tools

DESTRUCTIVE 3 tools

Destructive clean_proj Cleans build products for a specific project file using xcodebuild. IMPORTANT: Requires projectPath. Scheme/Co Destructive clean_ws Cleans build products for a specific workspace using xcodebuild. IMPORTANT: Requires workspacePath. Scheme/Con Destructive reset_simulator_location Resets the simulator

EXECUTE 17 tools

Execute boot_sim Boots an iOS simulator. IMPORTANT: You MUST provide the simulatorUuid parameter. Example: boot_sim({ simulator Execute button Press a hardware button on the simulator. Available buttons: apple-pay, home, lock, side-button, siri. Execute gesture Perform preset gesture patterns on the simulator. Available presets: scroll-up, scroll-down, scroll-left, scro Execute install_app_sim Installs an app in an iOS simulator. IMPORTANT: You MUST provide both the simulatorUuid and appPath parameters Execute key_press Press a single key by keycode on the simulator. Common keycodes: 40=Return, 42=Backspace, 43=Tab, 44=Space, 58 Execute key_sequence Press a sequence of keys by their keycodes on the simulator. Each key will be pressed and released before the Execute launch_app_logs_sim Launches an app in an iOS simulator and captures its logs. Execute launch_app_sim Launches an app in an iOS simulator. IMPORTANT: You MUST provide both the simulatorUuid and bundleId parameter Execute launch_mac_app Launches a macOS application. IMPORTANT: You MUST provide the appPath parameter. Example: launch_mac_app({ app Execute long_press Long press at specific coordinates for given duration (ms). Use describe_ui for precise coordinates (don Execute open_sim Opens the iOS Simulator app. Execute reset_network_condition Resets network conditions to default in the simulator. Execute set_network_condition Simulates different network conditions (e.g., wifi, 3g, edge, high-latency, dsl, 100%loss, 3g-lossy, very-loss Execute swipe Swipe from one point to another. Use describe_ui for precise coordinates (don Execute tap Tap at specific coordinates. Use describe_ui to get precise element coordinates (don Execute touch Perform touch down/up events at specific coordinates. Use describe_ui for precise coordinates (don Execute type_text Type text (supports US keyboard characters). Use describe_ui to find text field, tap to focus, then type.

WRITE 2 tools

Write set_sim_appearance Sets the appearance mode (dark/light) of an iOS simulator. Write set_simulator_location Sets a custom GPS location for the simulator.

READ 7 tools

Read describe_ui Gets entire view hierarchy with precise frame coordinates (x, y, width, height) for all visible elements. Use Read diagnostic Provides comprehensive information about the MCP server environment, available dependencies, and configuration Read discover_projs Scans a directory (defaults to workspace root) to find Xcode project (.xcodeproj) and workspace (.xcworkspace) Read get_ios_bundle_id Extracts the bundle identifier from an iOS app bundle (.app). IMPORTANT: You MUST provide the appPath paramete Read get_mac_bundle_id Extracts the bundle identifier from a macOS app bundle (.app). IMPORTANT: You MUST provide the appPath paramet Read list_sims Lists available iOS simulators with their UUIDs. Read screenshot Captures screenshot for visual verification. For UI coordinates, use describe_ui instead (don

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about Sl Test

Can an AI agent delete data through the Sl Test MCP server? +

Yes. The Sl Test server exposes 3 destructive tools including clean_proj, clean_ws, reset_simulator_location. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Sl Test? +

The Sl Test server has 2 write tools including set_sim_appearance, set_simulator_location. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Sl Test.

How many tools does the Sl Test MCP server expose? +

29 tools across 4 categories: Destructive, Execute, Read, Write. 7 are read-only. 22 can modify, create, or delete data.

How do I enforce a policy on Sl Test? +

Register the Sl Test MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Sl Test tool call.

Deterministic rules across all 29 Sl Test tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON SL TEST →

Instant setup, no code required.

29 Sl Test tools catalogued and risk-classified — across an index of 43,000+ MCP servers.