This record as markdown: /tools/alexgladkov-claude-in-mobile/visual-delete.md
What visual_delete does on Claude Mobile
AI agents call visual_delete to permanently remove resources in Claude Mobile, typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Why visual_delete is rated Critical
The tool performs an irreversible deletion operation on a visual baseline artifact. This falls clearly into the Destructive category as it cannot be undone and removes stored data. While the blast radius is scoped to visual baselines rather than production data or system files, unauthorized deletion of test/comparison baselines could disrupt QA workflows and testing pipelines, justifying 'high' severity.
From the tool's definition Tool name 'visual_delete' explicitly uses the verb 'delete' combined with 'visual baseline', indicating irreversible removal of data. The description states 'Delete a visual baseline' which confirms permanent data destruction.
Attacks that exploit this kind of access
The rule that runs visual_delete 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 visual_delete, this is the rule to start with:
visual_delete is removed from the agent's tool list entirely, so the agent never calls it. The rest of the server keeps working.
The button opens the PolicyLayer dashboard: create your workspace, connect Claude Mobile, apply this rule, and every visual_delete call is checked against it from then on.
Questions about visual_delete
Delete a visual baseline. It is categorised as a Destructive tool in the Claude Mobile MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Claude Mobile MCP server in PolicyLayer and add a rule for visual_delete: 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.
visual_delete is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the visual_delete 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 visual_delete. 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.
visual_delete 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