flow_parallel
Run same action on multiple devices in parallel. Uses Promise.allSettled for concurrent execution.
This record as markdown: /tools/alexgladkov-claude-in-mobile/flow-parallel.md
What flow_parallel does on Claude Mobile
AI agents invoke flow_parallel 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 flow_parallel is rated High
This is an Execute-category tool because it triggers external operations (device control actions) whose effects depend on the arguments passed—specifically, whatever action is being run on the devices in parallel.
From the tool's definition Tool description states 'Run same action on multiple devices in parallel' and 'concurrent execution'. The parent server enables 'control devices with natural language through screenshots, UI interactions, text input, and app management'.
Attacks that exploit this kind of access
The rule that runs flow_parallel 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 flow_parallel, this is the rule to start with:
flow_parallel 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 flow_parallel call is checked against it from then on.
Questions about flow_parallel
Run same action on multiple devices in parallel. Uses Promise.allSettled for concurrent execution. 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 flow_parallel: 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.
flow_parallel 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 flow_parallel 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 flow_parallel. 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.
flow_parallel 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