sync_run
Execute coordinated steps across devices with barrier synchronization.
This record as markdown: /tools/alexgladkov-claude-in-mobile/sync-run.md
What sync_run does on Claude Mobile
AI agents invoke sync_run 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 sync_run is rated High
This tool executes arbitrary coordinated steps across Android/iOS devices via ADB and simctl. While it does not permanently delete data or move money, it can trigger external operations (app interactions, UI automation, system commands) whose effects depend on the specific steps provided. The multi-device synchronization amplifies the blast radius—a misconfigured sequence could affect multiple devices simultaneously.
From the tool's definition Tool name 'sync_run' combined with description 'Execute coordinated steps across devices with barrier synchronization' explicitly uses the verb 'Execute' and indicates it runs coordinated operations across multiple mobile devices.
Attacks that exploit this kind of access
The rule that runs sync_run 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 sync_run, this is the rule to start with:
sync_run 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 sync_run call is checked against it from then on.
Questions about sync_run
Execute coordinated steps across devices with barrier synchronization. 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 sync_run: 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.
sync_run 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 sync_run 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 sync_run. 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.
sync_run 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