This record as markdown: /tools/alexgladkov-claude-in-mobile/sandbox-file-list.md
What sandbox_file_list does on Claude Mobile
AI agents call sandbox_file_list 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 sandbox_file_list is rated Low
This tool retrieves a directory listing of files within an app's sandbox environment. It is a read-only operation that queries the file system state without creating, modifying, deleting, or executing any code. The blast radius if misused is minimal—an agent could enumerate files to discover sensitive paths, but cannot directly access, modify, or delete them. Classified as Read with low severity.
From the tool's definition Tool name 'sandbox_file_list' and description 'List files inside an app' indicate a query/retrieval operation with no modification or deletion of data.
Attacks that exploit this kind of access
The rule that runs sandbox_file_list 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 sandbox_file_list, this is the rule to start with:
sandbox_file_list 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 sandbox_file_list call is checked against it from then on.
Questions about sandbox_file_list
List files inside an app. 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 sandbox_file_list: 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.
sandbox_file_list 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 sandbox_file_list 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 sandbox_file_list. 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.
sandbox_file_list 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