List all the available items in the registry
AI agents call get_items to retrieve information from Shadcn Registry manager without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns a list of available registry items. It performs no modifications, deletions, or external operations. The action is purely informational and read-only, fitting the 'Read' category. Severity is low because listing registry items poses minimal security risk—the data returned is metadata about available components, not sensitive user data or system-critical information.
From the tool's definition Tool name 'get_items' and description 'List all the available items in the registry' indicate a retrieval operation with no side effects.
Attacks that exploit this kind of access
List all the available items in the registry. It is categorised as a Read tool in the Shadcn Registry manager MCP Server, which means it retrieves data without modifying state.
Register the Shadcn Registry manager MCP server in PolicyLayer and add a rule for get_items: 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 Shadcn Registry manager. Nothing to install.
get_items 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 get_items 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 get_items. 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.
get_items is provided by the Shadcn Registry manager MCP server (reuvenaor/shadcn-registry-manager). 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 →