AI agents call storybook_list_components to retrieve information from Storybook without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool lists components, a pure data retrieval operation with no side effects. Even though the description is empty, the clear naming convention (list_*) and context as part of a Storybook browsing interface confirm this is Read category. Severity is low because listing existing components poses minimal risk—the blast radius of misuse is nearly zero.
From the tool's definition Tool name 'storybook_list_components' indicates a list operation, which is a read-only action that retrieves component metadata from a Storybook instance without modifying state.
Attacks that exploit this kind of access
storybook_list_components. It is categorised as a Read tool in the Storybook MCP Server, which means it retrieves data without modifying state.
Register the Storybook MCP server in PolicyLayer and add a rule for storybook_list_components: 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_list_components is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the storybook_list_components 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_list_components. 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_list_components 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 →