sandbox_file_read

Read the contents of a file from an app

SERVERClaude Mobile SOURCEalexgladkov/claude-in-mobile

Low RISK CLASS

Category Read

Parameters 00 required

Recommended Allowedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/alexgladkov-claude-in-mobile/sandbox-file-read.md

WHAT IT DOES

What sandbox_file_read does on Claude Mobile

AI agents call sandbox_file_read 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.

RISK

Why sandbox_file_read is rated Low

This tool retrieves file contents from an app's sandbox on a mobile device. It performs a query operation without creating, modifying, or deleting data. The scope is limited to reading app-sandboxed files, reducing the blast radius. Classification as Read is appropriate with high confidence.

From the tool's definition Tool name 'sandbox_file_read' and description 'Read the contents of a file from an app' clearly indicate data retrieval with no modification or side effects.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs sandbox_file_read 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_read, this is the rule to start with:

sandbox_file_read Allowed

sandbox_file_read is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "sandbox_file_read": {}
  }
}

ALLOW ONLY THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Claude Mobile, apply this rule, and every sandbox_file_read call is checked against it from then on.

FAQ

Questions about sandbox_file_read

What does the sandbox_file_read tool do? +

Read the contents of a file from an app. It is categorised as a Read tool in the Claude Mobile MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on sandbox_file_read? +

Register the Claude Mobile MCP server in PolicyLayer and add a rule for sandbox_file_read: 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.

What risk level is sandbox_file_read? +

sandbox_file_read is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit sandbox_file_read? +

Yes. Add a rate_limit block to the sandbox_file_read 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.

How do I block sandbox_file_read completely? +

Set action: deny in the PolicyLayer policy for sandbox_file_read. 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.

What MCP server provides sandbox_file_read? +

sandbox_file_read 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.

KEEP EXPLORING

More on Claude Mobile, and thousands of servers like it.

This server

All 198 Claude Mobile tools →

Across the catalogue

read_input_file on 0gzk →claude_read_file on Claude Bridge → The MCP Attack Database →

Guides

Roll out MCP under one policy →Data exfiltration →MCP token cost →