visual
Visual regression testing. baseline_save: capture baseline screenshot. compare: diff against baseline. baseline_update: overwrite baseline. list: show all baselines. delete: remove baseline. suite: batch comparison.
This record as markdown: /tools/alexgladkov-claude-in-mobile/visual.md
What visual does on Claude Mobile
AI agents call visual 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 is rated Critical
The tool includes operations that irreversibly overwrite or delete baseline screenshots ('baseline_update: overwrite baseline' and 'delete: remove baseline'). While some sub-operations are read/compare in nature, the most severe applicable category is Destructive due to the permanent deletion and overwrite capabilities.
From the tool's definition baseline_update: overwrite baseline. delete: remove baseline.
Attacks that exploit this kind of access
The rule that runs visual 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, this is the rule to start with:
visual 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 call is checked against it from then on.
Questions about visual
Visual regression testing. baseline_save: capture baseline screenshot. compare: diff against baseline. baseline_update: overwrite baseline. list: show all baselines. delete: remove baseline. suite: batch comparison. 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: 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 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 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. 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 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