Returns the JSX source code of a specific component.
AI agents call get_component to retrieve information from Grocers Design 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 existing design system component code. It performs a read-only lookup without creating, modifying, deleting, or executing any code. The returned JSX source is data retrieval, not execution. Blast radius is minimal: an agent can only access design system information that is already intended to be sharable within the design system context.
From the tool's definition Tool 'get_component' 'Returns the JSX source code of a specific component' — a retrieval operation with no side effects.
Attacks that exploit this kind of access
Returns the JSX source code of a specific component. It is categorised as a Read tool in the Grocers Design MCP Server, which means it retrieves data without modifying state.
Register the Grocers Design MCP server in PolicyLayer and add a rule for get_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 Grocers Design. Nothing to install.
get_component 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_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 get_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.
get_component is provided by the Grocers Design MCP server (rogerio-ignacio-filho/grocers-design-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 →