当用户请求一个新的用户界面（UI）使用 Ant Design 组件时使用此工具。 此工具仅返回可用的组件列表。 调用此工具后，你必须编辑或添加文件，以便将代码片段集成到代码库中
AI agents call list-components to retrieve information from Antd Components without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a Read operation—it queries and retrieves component information from Ant Design documentation without creating, modifying, deleting, or executing any code. The tool merely provides informational output to help users understand what components are available. The note about editing files afterward is a separate action performed by the user/AI agent, not by the tool itself.
From the tool's definition Tool description states 'this tool only returns a list of available components' (此工具仅返回可用的组件列表). The word 'list' and the function of returning available components without modification indicates pure data retrieval with no side effects.
Documented attack patterns abuse exactly the kind of access list-components gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Antd Components, and nothing reaches the server without passing your rules. This is the rule we recommend for list-components:
{
"version": "1",
"default": "deny",
"tools": {
"list-components": {}
}
}list-components is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
当用户请求一个新的用户界面（UI）使用 Ant Design 组件时使用此工具。 此工具仅返回可用的组件列表。 调用此工具后，你必须编辑或添加文件，以便将代码片段集成到代码库中. It is categorised as a Read tool in the Antd Components MCP Server, which means it retrieves data without modifying state.
Register the Antd Components MCP server in PolicyLayer and add a rule for 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 Antd Components. Nothing to install.
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 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 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.
list-components is provided by the Antd Components MCP server (zhixiaoqiang/antd-components-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 4 Antd Components tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4 Antd Components tools catalogued and risk-classified — across an index of 42,500+ MCP servers.