go_back

Press back button

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/go-back.md

WHAT IT DOES

What go_back does on Claude Mobile

AI agents invoke go_back 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 go_back is rated High

This tool executes a device-level UI action (pressing the back button) on Android or iOS, which is an external operation affecting device state. It fits the Execute category as it triggers a real interaction on a physical/simulated device. Severity is medium because misuse could navigate away from screens or disrupt app state, though it cannot directly delete data or move money.

From the tool's definition Press back button — triggers a UI interaction on a mobile device via ADB/simctl

Attacks that exploit this kind of access

RECOMMENDED RULE

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

go_back Rate-limited

go_back 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": {
    "go_back": {
      "limits": [
        {
          "counter": "go_back_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 go_back call is checked against it from then on.

FAQ

Questions about go_back

What does the go_back tool do? +

Press back button. 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 go_back? +

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

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

Can I rate-limit go_back? +

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

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

go_back 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

All high-risk MCP tools → The MCP Attack Database →

Guides

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