flow_run

Multi-step automation flow with conditionals, loops, error handling. Use for E2E testing instead of calling tools one-by-one. Set turbo:true for UI context per step (experimental). Max 20 steps.

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-run.md

WHAT IT DOES

What flow_run does on Claude Mobile

AI agents invoke flow_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.

RISK

Why flow_run is rated High

This tool orchestrates multi-step execution of device automation commands with control flow (conditionals, loops, error handling). While individual sibling tools like app_launch or accessibility are Write or Read operations, flow_run's ability to chain arbitrary sequences of these operations with programming constructs (conditionals, loops) and execute them as a unified procedure qualifies it as Execute rather than…

From the tool's definition Tool name 'flow_run' with description enabling 'multi-step automation flow with conditionals, loops, error handling' on mobile devices controlled via ADB/simctl.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs flow_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 flow_run, this is the rule to start with:

flow_run Rate-limited

flow_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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "flow_run": {
      "limits": [
        {
          "counter": "flow_run_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_run call is checked against it from then on.

FAQ

Questions about flow_run

What does the flow_run tool do? +

Multi-step automation flow with conditionals, loops, error handling. Use for E2E testing instead of calling tools one-by-one. Set turbo:true for UI context per step (experimental). Max 20 steps. 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_run? +

Register the Claude Mobile MCP server in PolicyLayer and add a rule for flow_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.

What risk level is flow_run? +

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

Can I rate-limit flow_run? +

Yes. Add a rate_limit block to the flow_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.

How do I block flow_run completely? +

Set action: deny in the PolicyLayer policy for flow_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.

What MCP server provides flow_run? +

flow_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.

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

run on 0sec →shortcuts_run on Apple Apps MCP →run_emba_scan on EMBA-MCP → All high-risk MCP tools → The MCP Attack Database →

Guides

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