// SCAN REPORT

RunCue

4 tools. 1 can modify or destroy data without limits.

1 write tool that can modify data. Rate limits recommended.

Last updated: 2 Jul 2026

1 can modify or destroy data

3 read-only

4 tools total

Community server · catalogue entry verified 02/07/2026

How to control RunCue ↓

TOOL MAP

What RunCue exposes to your agents

Read (3) Write / Execute (1) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous RunCue tools

Execute · High runcue_run This tool executes arbitrary UI automation workflows on iOS devices via WebDriverAgent.

1 of RunCue's 4 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control RunCue

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

Cap read operations

{
  "runcue_check": {
    "limits": [
      {
        "counter": "runcue_check_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 RunCue — 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 RUNCUE →

Instant setup, no code required.

FULL CATALOGUE

All 4 RunCue tools

EXECUTE 1 tools

Execute runcue_run Execute a multi-step UI task on an iOS Simulator or physical iOS device autonomously. RunCue uses WDA (WebDri

READ 3 tools

Read runcue_check Analyze the current UI state without performing any actions. Returns both a VLM-generated text description an Read runcue_devices List iOS devices and simulators visible to Xcode. Use this first when you do not know the exact deviceId. Pass Read runcue_doctor Diagnose RunCue WDA setup for a simulator or physical iOS device. Use when runcue_run fails with device, signi

EXPLORE

Related servers

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

FAQ

Questions about RunCue

Is the RunCue MCP server safe to use without restrictions? +

The RunCue server is primarily read-only with 3 read tools. While it cannot modify data, an agent in a retry loop can make thousands of API calls per minute, exhausting rate limits and running up costs. Rate limiting is still recommended.

How many tools does the RunCue MCP server expose? +

4 tools across 2 categories: Execute, Read. 3 are read-only. 1 can modify, create, or delete data.

How do I enforce a policy on RunCue? +

Register the RunCue 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 RunCue tool call.

Deterministic rules across all 4 RunCue tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON RUNCUE →

Instant setup, no code required.

4 RunCue tools catalogued and risk-classified — across an index of 43,000+ MCP servers.