Run visual and accessibility tests on a component
AI agents invoke storybook_test_component to trigger actions in UI/UX MCP Server. 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.
This tool executes test suites (visual and accessibility) against components. It triggers external test runners and browser automation, making it an Execute category tool. Misuse could cause unintended side effects like overwriting baseline screenshots or consuming significant resources, hence medium severity.
From the tool's definition Run visual and accessibility tests on a component
Attacks that exploit this kind of access
Run visual and accessibility tests on a component. It is categorised as a Execute tool in the UI/UX MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the UI/UX MCP Server MCP server in PolicyLayer and add a rule for storybook_test_component: 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 UI/UX MCP Server. Nothing to install.
storybook_test_component 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 storybook_test_component 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 storybook_test_component. 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.
storybook_test_component is provided by the UI/UX MCP Server MCP server (willem4130/ui-ux-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 →