AI agents invoke start-server to trigger actions in ADB MCP Server. 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.
Starting a server process is an Execute action because it runs an external operation with side effects that extend beyond simple data retrieval or modification. While not immediately destructive, it creates a persistent system resource and could enable subsequent misuse of ADB functionality (e.g., unauthorized device access, app installation, or file manipulation).
From the tool's definition Tool name 'start-server' indicates it 'Start[s] the ADB server process', which triggers an external system operation (starting a service/daemon). This is an execution action that initiates a background process whose behavior depends on system configuration.
Documented attack patterns abuse exactly the kind of access start-server gives an agent:
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-server:
{
"version": "1",
"default": "deny",
"tools": {
"start-server": {
"limits": [
{
"counter": "start-server_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}start-server 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.
Free to start. No card required.
Start the ADB server process. 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.
Register the ADB MCP Server MCP server in PolicyLayer and add a rule for start-server: 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.
start-server is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the start-server 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.
Set action: deny in the PolicyLayer policy for start-server. 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.
start-server 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.
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.
Free to start. No card required.
30 ADB MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.