start_pipeline · Maa MCP: Risk & Policy

WHAT IT DOES

What start_pipeline does on MaaMCP

AI agents invoke start_pipeline to trigger actions in MaaMCP. 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.

WHY IT NEEDS A POLICY

Why start_pipeline needs a policy

Starting a pipeline in an automation framework executes external operations whose effects depend on the pipeline's configuration and contents. While the description is empty (lowering confidence slightly), the context of Android/Windows automation, combined with sibling tools that interact with devices and UIs, strongly suggests this triggers automated actions.

From the tool's definition Tool named 'start_pipeline' on a server that provides 'Android device and Windows desktop automation capabilities.' The sibling tools include device connection (connect_adb_device, connect_window), UI interaction (click, double_click, click_key), and resource…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

start_pipeline Rate-limited

start_pipeline 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.

View as policy code

policy.json

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

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches MaaMCP, so you can run agents against it safely.

FAQ

Questions about start_pipeline

What does the start_pipeline tool do? +

start_pipeline. It is categorised as a Execute tool in the MaaMCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on start_pipeline? +

Register the Maa MCP server in PolicyLayer and add a rule for start_pipeline: 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 MaaMCP. Nothing to install.

What risk level is start_pipeline? +

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

Can I rate-limit start_pipeline? +

Yes. Add a rate_limit block to the start_pipeline 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 start_pipeline completely? +

Set action: deny in the PolicyLayer policy for start_pipeline. 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 start_pipeline? +

start_pipeline is provided by the Maa MCP server (maa-ai/maamcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.