flow
Flow orchestration: batch (multi-command), run (multi-step automation with loops/conditionals), parallel (same action on multiple devices). Use turbo:true for rich feedback (experimental).
This record as markdown: /tools/alexgladkov-claude-in-mobile/flow.md
What flow does on Claude Mobile
AI agents invoke flow 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 is rated High
The flow tool orchestrates and executes sequences of commands on mobile devices with conditional logic and looping. This goes beyond simple read/write operations—it runs arbitrary multi-step automation workflows that can trigger side effects across devices.
From the tool's definition Tool performs 'batch (multi-command)', 'run (multi-step automation with loops/conditionals)', and 'parallel (same action on multiple devices)' operations on mobile devices controlled via ADB and simctl.
Attacks that exploit this kind of access
The rule that runs flow 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, this is the rule to start with:
flow 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 call is checked against it from then on.
Questions about flow
Flow orchestration: batch (multi-command), run (multi-step automation with loops/conditionals), parallel (same action on multiple devices). Use turbo:true for rich feedback (experimental). 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: 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 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 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. 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 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