Agentify Components
by anvosio
A framework for adding semantic metadata to React components, making them "agent-aware" for AI systems and automation tools. It solves the problem of making UI components understandable to AI agents by adding a semantic layer through decorators.
Last updated: 2025-03-14
What is Agentify Components?
Agentify Components is a framework that adds a semantic layer to React components, making them understandable to AI agents. It provides decorators to register component metadata, a standardized schema, and generates configuration files for an MCP server.
How to use Agentify Components?
Install the package using npm install @anvosio/agentify-components. Then, use the @AgentConfig decorator or the withAgentConfig HOC to add metadata to your components. Finally, use the provided CLI tool to generate the MCP server.
Key features of Agentify Components
Registers component metadata
Provides a standardized schema for metadata
Generates configuration files for MCP server
Supports multiple component types (Search Bars, Forms, Buttons)
Flexible architecture with decorators, transformers, and generators
Use cases of Agentify Components
Enabling AI assistants to interact with web applications
Making UI components self-describing to AI systems
Connecting AI models with external data sources and tools
Simplifying integrations with a universal protocol for secure and standardized connections
FAQ from Agentify Components
What is MCP?
What is MCP?
The Model Context Protocol (MCP) is an open standard developed by Anthropic to connect AI models with external data sources and tools.
What component types are supported?
What component types are supported?
Currently supports API and Navigation behaviours.
How do I install Agentify Components?
How do I install Agentify Components?
You can install it using npm: npm install @anvosio/agentify-components.
How do I generate the MCP server?
How do I generate the MCP server?
Add a generate.ts file and scripts to your package.json, then run npm run build:mcp.
How do I contribute to the project?
How do I contribute to the project?
Contributions are welcome! Please feel free to submit a Pull Request.