MCP.so
ログイン

Agentify Components MCP Server

@anvosio

基本情報

カテゴリ

その他

ライセンス

MIT

トランスポート

stdio

作者

anvosio

Agentify Components MCP Server について

These are the components that a user can download to create MCP servers on the fly

Agentify Components MCP Server の設定

標準の設定はありません

このサーバーの README には解析可能な MCP 設定ブロックが含まれていません。インストール手順はリポジトリをご確認ください。

リポジトリ

Agentify Components MCP Server のツール

ツール一覧はまだありません

この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

What is Agentify Components?

Agentify Components is a framework that adds semantic metadata to React components, making them “agent-aware” for AI systems and automation tools. It integrates with the Model Context Protocol (MCP) to generate a runnable MCP server from annotated components, enabling AI assistants to understand and interact with UI elements.

How to use Agentify Components?

Install via npm install @anvosio/agentify-components. Annotate React components using the @AgentConfig decorator, the withAgentConfig HOC, or a direct agentConfig property. Create a generate.ts script that calls generateMCPServer(componentList, './mcpServer'), then run npm run build:mcp to produce the MCP server; npm run deploy:mcp publishes it.

Key features of Agentify Components

  • Adds semantic metadata to React components
  • Supports three component types: search bars, forms, buttons
  • Provides decorator, HOC, and property-assignment patterns
  • Generates an MCP server at build time
  • Architecture with Decorator, Transformers, Generators, and CLI Tool

Use cases of Agentify Components

  • Make a product search component self-describing to AI agents
  • Allow AI assistants to understand and submit login forms intelligently
  • Enable AI to identify and trigger navigation or API buttons
  • Build an MCP server that exposes frontend UI behaviors as tools for LLMs

よくある質問

1

What does Agentify Components do?

It adds a semantic layer to React components so that AI agents can understand their purpose, behavior, and data handling without changing component functionality.

2

What component types are supported?

Search bars, forms, and buttons are supported. Currently, behaviors are limited to API and navigation actions.

3

How do I annotate a component?

Use the `@AgentConfig` decorator for class components, the `withAgentConfig` HOC for functional components, or assign an `agentConfig` property directly to a functional component.

4

How is the MCP server generated?

Add a `generate.ts` script that imports your components and calls `generateMCPServer(componentList, './mcpServer')`. Run `npm run build:mcp` to generate the server files.

5

Is Agentify Components only for class components?

No. Functional components can be annotated using the HOC (`withAgentConfig`) or the direct property assignment pattern.

コメント

「その他」の他のコンテンツ