run_orchestrator

THE RISK

High Risk

Why run_orchestrator needs a policy

This tool triggers execution of a mobile test automation pipeline involving multiple coordinated agents. The orchestration process will execute test plans, generate test code, and apply self-healing logic against actual Android/iOS targets. The effects are determined by the pipeline configuration and arguments passed, and the tool enables running arbitrary test automation workflows.

From the tool's definition Tool description states 'Run Android or iOS orchestration pipeline' - the verb 'Run' combined with orchestration of multiple agents (Planner, Generator, Healer) indicates execution of complex, multi-step operations whose effects depend on the orchestration…

Documented attack patterns abuse exactly the kind of access run_orchestrator gives an agent:

POLICY

How to control run_orchestrator

PolicyLayer is an MCP gateway — it sits between your AI agents and Mobile Testing AI Agent MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for run_orchestrator:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "run_orchestrator": {
      "limits": [
        {
          "counter": "run_orchestrator_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

run_orchestrator stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

Create a free account and register Mobile Testing AI Agent MCP Server — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

RATE-LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Mobile Testing AI Agent MCP Server tools

Execute run_generator Run Generator agent to create executable tests from a Markdown plan. Execute run_healer Run Healer agent to execute and auto-repair failing tests. Execute run_planner Run Planner agent to generate a Markdown test plan from a target URL. Read health_check Get basic MCP server and environment health information. Read list_repo_commands Return frequently used npm commands for this repository.

All 6 Mobile Testing AI Agent MCP Server tools →

Execute tools on other servers

Android Forensics ADB MCP Server adb_shell_command EMBA-MCP run_emba_scan Frida Game Hacking MCP remove_breakpoint Procmon request_elevation

Go deeper

High-risk tools in Mobile Testing AI Agent MCP Server → Every high-risk tool this server exposes, in one view.
All high-risk MCP tools → Every high-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Agent sandbox → Bounding what an agent can execute and where the boundary should sit.
Least privilege for MCP → Granting agents the minimum tool surface the task needs.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about run_orchestrator

What does the run_orchestrator tool do? +

Run Android or iOS orchestration pipeline (Planner -> Generator -> Healer). It is categorised as a Execute tool in the Mobile Testing AI Agent MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on run_orchestrator? +

Register the Mobile Testing AI Agent MCP Server MCP server in PolicyLayer and add a rule for run_orchestrator: 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 Mobile Testing AI Agent MCP Server. Nothing to install.

What risk level is run_orchestrator? +

run_orchestrator is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit run_orchestrator? +

Yes. Add a rate_limit block to the run_orchestrator 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.

How do I block run_orchestrator completely? +

Set action: deny in the PolicyLayer policy for run_orchestrator. 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.

What MCP server provides run_orchestrator? +

run_orchestrator is provided by the Mobile Testing AI Agent MCP Server MCP server (padmarajnidagundi/mobile-app-testing-ai-agent-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Mobile Testing AI Agent MCP Server tool call.

Start from Mobile Testing AI Agent MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →