recorder_play
Replay a saved scenario. Executes all steps sequentially with optional speed/timeout control.
This record as markdown: /tools/alexgladkov-claude-in-mobile/recorder-play.md
What recorder_play does on Claude Mobile
AI agents invoke recorder_play 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 recorder_play is rated High
This tool executes a pre-recorded sequence of UI interactions and device operations. Since it can replay arbitrary automation steps (which may include app installs, text input, UI interactions, or other operations), it falls under Execute.
From the tool's definition 'Replay a saved scenario. Executes all steps sequentially' - the tool runs a sequence of recorded actions on a mobile device
Attacks that exploit this kind of access
The rule that runs recorder_play 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 recorder_play, this is the rule to start with:
recorder_play 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 recorder_play call is checked against it from then on.
Questions about recorder_play
Replay a saved scenario. Executes all steps sequentially with optional speed/timeout control. 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 recorder_play: 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.
recorder_play 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 recorder_play 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 recorder_play. 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.
recorder_play 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