AI agents call memory-info to retrieve information from ADB MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves read-only memory statistics from an Android device. It performs no data modification, deletion, code execution, or financial operations. The action is informational and non-destructive. Severity is low because memory information is not sensitive system data that would cause significant harm if exposed to or misused by an AI agent.
From the tool's definition Tool name 'memory-info' and description '查看设备内存使用情况' (view device memory usage) indicate querying/retrieving system information without modification or side effects.
Documented attack patterns abuse exactly the kind of access memory-info 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 memory-info:
{
"version": "1",
"default": "deny",
"tools": {
"memory-info": {}
}
}memory-info is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
查看设备内存使用情况. It is categorised as a Read tool in the ADB MCP Server MCP Server, which means it retrieves data without modifying state.
Register the ADB MCP Server MCP server in PolicyLayer and add a rule for memory-info: 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.
memory-info is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the memory-info 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 memory-info. 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.
memory-info 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.