adb_start_activity · Openclaw Adb MCP: Risk & Policy

WHAT IT DOES

What adb_start_activity does on Openclaw Adb

AI agents invoke adb_start_activity to trigger actions in Openclaw Adb. 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 adb_start_activity needs a policy

This tool launches Android activities, which are executable operations that perform actions determined by the intent parameter. The effects depend entirely on which activity is started—it could launch any app, trigger any app feature, or initiate system operations. While not inherently destructive or financial, it enables arbitrary code execution on a connected Android device, making it Execute category.

From the tool's definition The tool 'adb_start_activity' with description 'Start an activity with the given intent' executes commands on an Android device that trigger application activities based on provided intent arguments.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

adb_start_activity Rate-limited

adb_start_activity 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": {
    "adb_start_activity": {
      "limits": [
        {
          "counter": "adb_start_activity_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 Openclaw Adb, so you can run agents against it safely.

FAQ

Questions about adb_start_activity

What does the adb_start_activity tool do? +

Start an activity with the given intent. It is categorised as a Execute tool in the Openclaw Adb MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on adb_start_activity? +

Register the Openclaw Adb MCP server in PolicyLayer and add a rule for adb_start_activity: 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 Openclaw Adb. Nothing to install.

What risk level is adb_start_activity? +

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

Can I rate-limit adb_start_activity? +

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

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

adb_start_activity is provided by the Openclaw Adb MCP server (wilsonbeam/openclaw-adb-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.