Exploring the Application of AI Agents in the Web3 Field: From Manus to MC

Recently, a general AI Agent product named Manus has attracted wide attention. As the world's first general AI Agent, Manus demonstrates strong independent thinking and the ability to execute complex tasks, providing new ideas for the development of AI Agents. With the rapid development of AI technology, AI Agents, as an important branch of artificial intelligence, are showing great potential in various industries, and the Web3 industry is no exception.

Overview of AI Agent

An AI Agent is a computer program that can autonomously make decisions and execute tasks based on the environment, inputs, and predefined goals. Its core components include a large language model (LLM) as the "brain", observation and perception mechanisms, reasoning and thinking processes, action execution, and memory and retrieval functions.

The design patterns of AI Agents mainly have two development routes: one focuses on planning ability, and the other emphasizes reflective ability. Among them, the ReAct model is currently the most widely used design pattern, with a typical process that includes three steps: thinking, acting, and observing, forming a cyclical iterative process.

According to the number of agents, AI Agents can be divided into Single Agent and Multi Agent. Single Agent focuses on the combination of LLM and tools, while Multi Agent assigns different roles to different agents to collaboratively complete complex tasks.

Model Context Protocol (MCP)

MCP is an open-source protocol designed to address the connection and interaction issues between LLMs and external data sources. It offers three capabilities to extend LLMs: knowledge expansion, executing function calls to external systems, and pre-written prompt templates. MCP adopts a Client-Server architecture, and the underlying transport uses the JSON-RPC protocol.

The Current State of AI Agents in Web3

The popularity of AI Agents in the Web3 industry peaked in January this year but has since declined, although some projects still maintain a high level of attention. The main modes include three types:

1. Launch Platform Mode: Represented by Virtuals Protocol, allows users to create, deploy, and monetize AI Agents.
2. DAO Model: Represented by ElizaOS, decisions are made based on AI models and suggestions from DAO members.
3. Business Company Model: Represented by Swarms, providing an enterprise-level Multi Agent framework.

From the perspective of economic models, currently only the launch platform model can achieve a self-sustaining economic closed loop. However, this model also faces challenges, as the assets to be issued must have sufficient attractiveness to form a positive cycle.

Exploration Directions of MCP in Web3

The emergence of MCP has brought new exploration directions for Web3's AI Agent:

1. Deploy the MCP Server to the blockchain network to solve the single point issue and possess censorship resistance.
2. Enable MCP Server to interact with the blockchain, such as conducting DeFi transactions and management.
3. Build an Ethereum-based OpenMCP.Network creator incentive network, achieving automation, transparency, and trust in incentives through smart contracts.

Although the integration of MCP and Web3 can theoretically inject decentralized trust mechanisms and economic incentives into AI Agent applications, the current level of technology still struggles to fully verify the authenticity of Agent behaviors, and the efficiency issues of decentralized networks also need to be addressed.

Summary

The release of Manus marks an important milestone for general AI Agent products. The Web3 space also needs a milestone product to break the skepticism about its practicality. The emergence of MCP brings new exploration directions for AI Agents in Web3, including blockchain deployment, blockchain interaction capabilities, and the construction of a creator incentive network.

The integration of AI and Web3 is an inevitable trend. Although we still face many challenges at present, we need to maintain patience and confidence while continuously exploring this promising field.