start-activity

THE RISK

High Risk

Why start-activity needs a policy

This tool directly executes commands on an Android device via the activity manager. While not immediately destructive or financial, it can trigger side effects based on the activity argument—ranging from launching benign apps to initiating sensitive system operations, making it an Execute-category risk.

From the tool's definition The tool uses 'am start' to start an activity on an Android device. This executes code/operations on the target device whose effects depend on which activity is specified as an argument.

Documented attack patterns abuse exactly the kind of access start-activity gives an agent:

POLICY

How to control start-activity

PolicyLayer is an MCP gateway — it sits between your AI agents and ADB MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for start-activity:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "start-activity": {
      "limits": [
        {
          "counter": "start-activity_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

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.

Create a free account and register ADB 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 ADB MCP Server tools

Destructive clear-app-data Clear application data for a specific package Destructive clear-logcat 清除设备上的日志缓冲区 Destructive reset-permissions Reset all permissions for a specific package Destructive revoke-permission Revoke a specific permission from an app Destructive rm Remove a file from the Android device Destructive uninstall-apk Uninstall an application from the device Destructive kill-server Kill the ADB server process Execute start-server Start the ADB server process

All 30 ADB 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 ADB 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 start-activity

What does the start-activity tool do? +

Start an activity using activity manager (am start). It is categorised as a Execute tool in the ADB 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 start-activity? +

Register the ADB MCP Server MCP server in PolicyLayer and add a rule for 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 ADB MCP Server. Nothing to install.

What risk level is start-activity? +

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

Can I rate-limit start-activity? +

Yes. Add a rate_limit block to the 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 start-activity completely? +

Set action: deny in the PolicyLayer policy for 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 start-activity? +

start-activity is provided by the ADB MCP Server MCP server (jiantao88/android-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 ADB MCP Server tool call.

Start from ADB 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 →