system
System operations, clipboard, permissions, files. shell: run command. logs: device logs. clipboard_*: Android clipboard. permission_*: app permissions. file_*: Aurora file transfer.
This record as markdown: /tools/alexgladkov-claude-in-mobile/system.md
What system does on Claude Mobile
AI agents invoke system to trigger actions in Claude Mobile. 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 system is rated High
The ability to run arbitrary shell commands on a mobile device is a classic Execute category risk. While clipboard and file operations could be Read or Write in isolation, the inclusion of shell command execution elevates this to Execute. An AI agent with shell access could execute potentially harmful commands, modify system state, install malware, exfiltrate data, or compromise device security.
From the tool's definition Tool enables shell command execution ('shell: run command'), device log access ('logs: device logs'), clipboard operations ('clipboard_*: Android clipboard'), permission management ('permission_*: app permissions'), and file operations ('file_*: Aurora file…
Attacks that exploit this kind of access
The rule that runs system 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, this is the rule to start with:
system 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.
The button opens the PolicyLayer dashboard: create your workspace, connect Claude Mobile, apply this rule, and every system call is checked against it from then on.
Questions about system
System operations, clipboard, permissions, files. shell: run command. logs: device logs. clipboard_*: Android clipboard. permission_*: app permissions. file_*: Aurora file transfer. It is categorised as a Execute tool in the Claude Mobile MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Claude Mobile MCP server in PolicyLayer and add a rule for system: 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 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 system 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. 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 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.
Across the catalogue