AI agents use storybook_create_component to create or update resources in Storybook — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Storybook environment.
This tool creates new components in Storybook, a reversible write operation. The empty description lowers confidence slightly, but the name and sibling tools (which include list and get operations) confirm it modifies the component registry. Not Destructive because creation is not irreversible (components can be deleted separately).
From the tool's definition Tool name 'storybook_create_component' indicates creation of a component artifact. While the description is empty, the verb 'create' and the context of a Storybook integration (which manages UI component definitions and stories) imply the tool writes/creates…
Attacks that exploit this kind of access
storybook_create_component. It is categorised as a Write tool in the Storybook MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Storybook MCP server in PolicyLayer and add a rule for storybook_create_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 Storybook. Nothing to install.
storybook_create_component 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 storybook_create_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_create_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_create_component is provided by the Storybook MCP server (stevebrownlee/storybook-mcp). 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 →