app_install
Install APK (Android) or .app bundle (iOS)
This record as markdown: /tools/alexgladkov-claude-in-mobile/app-install.md
What app_install does on Claude Mobile
AI agents invoke app_install 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 app_install is rated High
Installing an application on a device is an external operation that deploys code onto the device, which can have significant security implications. It is not a simple write (data modification) but rather executes the installation process and deploys potentially arbitrary code. Misuse could result in malicious apps being installed on managed devices, making severity high.
From the tool's definition Install APK (Android) or .app bundle (iOS)
Attacks that exploit this kind of access
The rule that runs app_install 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 app_install, this is the rule to start with:
app_install 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 app_install call is checked against it from then on.
Questions about app_install
Install APK (Android) or .app bundle (iOS). 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 app_install: 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.
app_install 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 app_install 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 app_install. 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.
app_install 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