flow_batch

Execute multiple commands in one round-trip. Set turbo:true for UI context per step (experimental).

SERVERClaude Mobile SOURCEalexgladkov/claude-in-mobile

High RISK CLASS

Category Execute

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/flow-batch.md

WHAT IT DOES

What flow_batch does on Claude Mobile

AI agents invoke flow_batch 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.

RISK

Why flow_batch is rated High

This tool executes arbitrary sequences of commands on mobile devices through ADB and simctl. While individual commands might be reads or writes, the batch execution capability with UI context awareness allows an AI agent to chain together potentially harmful operations (app installations, system changes, input injection) in a single round-trip.

From the tool's definition Tool description states 'Execute multiple commands in one round-trip' with capability to set 'turbo:true for UI context per step'.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs flow_batch 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_batch, this is the rule to start with:

flow_batch Rate-limited

flow_batch 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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "flow_batch": {
      "limits": [
        {
          "counter": "flow_batch_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-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 flow_batch call is checked against it from then on.

FAQ

Questions about flow_batch

What does the flow_batch tool do? +

Execute multiple commands in one round-trip. Set turbo:true for UI context per step (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.

How do I enforce a policy on flow_batch? +

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

flow_batch is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit flow_batch? +

Yes. Add a rate_limit block to the flow_batch 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 flow_batch completely? +

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

flow_batch 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 → High-risk tools on this server →

Across the catalogue

qt_batch on Qt → All high-risk MCP tools → The MCP Attack Database →

Guides

Govern code and CI agents →Agent sandbox →Least privilege for MCP →