Visual regression: capture current screen (or crop by selector), pixel-diff against baseline PNG; use to verify UI didn’t change or to update baseline.
AI agents use visual_compare to create or update resources in React Native — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your React Native environment.
The primary operation is a visual regression check (Read/Execute), but the tool can also 'update baseline', which writes/overwrites the baseline PNG file. Since updating a baseline is a reversible write operation (overwriting a file), Write is the most severe applicable category. Misuse could silently update baselines to incorrect states, masking UI regressions.
From the tool's definition 'capture current screen... pixel-diff against baseline PNG... or to update baseline'
Attacks that exploit this kind of access
Visual regression: capture current screen (or crop by selector), pixel-diff against baseline PNG; use to verify UI didn’t change or to update baseline. It is categorised as a Write tool in the React Native MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the React Native MCP server in PolicyLayer and add a rule for visual_compare: 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 React Native. Nothing to install.
visual_compare is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the visual_compare 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_compare. 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_compare is provided by the React Native MCP server (@ohah/react-native-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →