This record as markdown: /tools/alexgladkov-claude-in-mobile/system-info.md
What system_info does on Claude Mobile
AI agents call system_info to retrieve information from Claude Mobile without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why system_info is rated Low
This tool only retrieves information about device battery and memory status. It has no side effects, does not execute code or commands, does not modify data, and does not delete or commit financial operations. It is a straightforward information-gathering operation with minimal blast radius if invoked incorrectly by an AI agent.
From the tool's definition Tool name 'system_info' and description 'Get battery and memory info' indicate a read-only query operation that retrieves system status without modifying or executing anything.
Risk signalsAdmin/system-level operation
Attacks that exploit this kind of access
The rule that runs system_info safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Claude Mobile, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For system_info, this is the rule to start with:
system_info is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Claude Mobile, apply this rule, and every system_info call is checked against it from then on.
Questions about system_info
Get battery and memory info. It is categorised as a Read tool in the Claude Mobile MCP Server, which means it retrieves data without modifying state.
Register the Claude Mobile MCP server in PolicyLayer and add a rule for system_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 Claude Mobile. Nothing to install.
system_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 system_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 system_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.
system_info is provided by the Claude Mobile MCP server (alexgladkov/claude-in-mobile). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Claude Mobile, and thousands of servers like it.
This server
Across the catalogue