List all the available blocks from the local blocks.json file
AI agents call get_blocks 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 retrieves and queries data from a local configuration file without creating, modifying, deleting, or executing anything. It is a straightforward read operation with minimal blast radius if misused by an AI agent.
From the tool's definition Tool name is 'get_blocks' and description states it 'List all the available blocks from the local blocks.json file' — a pure read operation with no modifications or side effects.
Attacks that exploit this kind of access
List all the available blocks from the local blocks.json file. 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_blocks: 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_blocks 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_blocks 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_blocks. 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_blocks 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 →