repl_spawn

Start an interactive REPL or CLI process under a PTY. Returns the session id.

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/repl-spawn.md

WHAT IT DOES

What repl_spawn does on Claude Mobile

AI agents invoke repl_spawn 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 repl_spawn is rated High

Starting a REPL/CLI process under a PTY is a direct mechanism for code execution. While not inherently destructive, it grants the ability to execute arbitrary commands whose effects depend entirely on what is run. In a mobile device automation context, this could access device internals, modify system state, extract data, or trigger device actions.

From the tool's definition Tool starts an interactive REPL or CLI process, which allows execution of arbitrary commands on the device. Combined with the server's mobile automation context (ADB for Android, simctl for iOS), this permits running shell commands on connected devices.

Attacks that exploit this kind of access

RECOMMENDED RULE

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

repl_spawn Rate-limited

repl_spawn 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": {
    "repl_spawn": {
      "limits": [
        {
          "counter": "repl_spawn_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 repl_spawn call is checked against it from then on.

FAQ

Questions about repl_spawn

What does the repl_spawn tool do? +

Start an interactive REPL or CLI process under a PTY. Returns the session id. 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 repl_spawn? +

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

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

Can I rate-limit repl_spawn? +

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

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

repl_spawn 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

spawn on Frida Game Hacking MCP → All high-risk MCP tools → The MCP Attack Database →

Guides

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