sandbox_prefs_write

Write or update a single value in an app

SERVERClaude Mobile SOURCEalexgladkov/claude-in-mobile

Medium RISK CLASS

Category Write

Parameters 00 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/alexgladkov-claude-in-mobile/sandbox-prefs-write.md

WHAT IT DOES

What sandbox_prefs_write does on Claude Mobile

AI agents use sandbox_prefs_write to create or update resources in Claude Mobile, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Claude Mobile environment.

RISK

Why sandbox_prefs_write is rated Medium

This tool creates or modifies application settings/preferences on a mobile device. While the changes are reversible (preferences can be updated again), the blast radius is medium because unintended preference changes could alter app behavior, disable features, or expose sensitive configuration.

From the tool's definition Tool name includes 'write' and description states 'Write or update a single value in an app', indicating reversible modification of application preferences/configuration.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs sandbox_prefs_write 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_prefs_write, this is the rule to start with:

sandbox_prefs_write Rate-limited

sandbox_prefs_write stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "sandbox_prefs_write": {
      "limits": [
        {
          "counter": "sandbox_prefs_write_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT 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_prefs_write call is checked against it from then on.

FAQ

Questions about sandbox_prefs_write

What does the sandbox_prefs_write tool do? +

Write or update a single value in an app. It is categorised as a Write tool in the Claude Mobile MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on sandbox_prefs_write? +

Register the Claude Mobile MCP server in PolicyLayer and add a rule for sandbox_prefs_write: 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_prefs_write? +

sandbox_prefs_write is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit sandbox_prefs_write? +

Yes. Add a rate_limit block to the sandbox_prefs_write 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_prefs_write completely? +

Set action: deny in the PolicyLayer policy for sandbox_prefs_write. 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_prefs_write? +

sandbox_prefs_write 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

write_file on 0sec →team_manager_write_memory on Team Manager MCP → The MCP Attack Database →

Guides

Govern customer-ops agents →Argument validation →Scoped token →