Want to connect with Chantastic (Michael Chan)?
Join organizations building the agentic web. Get introductions, share updates, and shape the future of .agent.
Is this your company?
Claim this profile to update your info, add products, and connect with the community.
Michael Chan is a primary advocate and educator for the Model Context Protocol (MCP), which is the emerging standard for connecting AI models to external tools and data. His work is critical for the agent ecosystem because it focuses on the connectivity layer—the infrastructure that allows agents to move beyond simple chat and into active tool use.
He matters to developers because he provides the practical implementations of MCP that allow disparate systems to speak the same language. By championing open standards over proprietary wrappers, he is helping prevent fragmentation in the agent stack. His contributions are centered on making the 'agent-to-data' interface as standardized as the web's existing API ecosystem.
Michael Chan, widely known in the developer community as Chantastic, is a technical educator and strategist who has become a prominent voice in the transition from traditional web development to agent-integrated systems. Based in Vista, California, Chan built his reputation within the React ecosystem, specifically as the host of the React Podcast and a contributor to various component-driven design initiatives. His career is characterized by an ability to take complex architectural patterns and distill them into actionable developer workflows.
Today, Chan’s focus is increasingly centered on the Model Context Protocol (MCP). MCP is an open standard designed to connect Large Language Models (LLMs) to external data sources and tools, effectively providing the 'connective tissue' for AI agents. While the protocol was introduced by major players like Anthropic, its adoption by the broader developer community requires translators. Chan fills this role by producing technical deep-dives, GitHub repositories, and blog posts that explain how to build and deploy MCP servers.
A core tenet of Chan’s work is the philosophy of "extract, don't abstract." This principle encourages developers to identify existing patterns in their codebases and expose them rather than building layers of speculative complexity. In the context of AI agents, this means creating clean, direct interfaces for agents to interact with data. By advocating for these standards, Chan helps developers avoid the trap of building brittle, proprietary integrations that fail to scale as the agent ecosystem evolves.
His work is particularly relevant for frontend and full-stack engineers who are tasked with making their applications "agent-ready." This involves not just building chat interfaces, but ensuring that the underlying data and tool sets are discoverable and usable by autonomous or semi-autonomous agents. Chan’s tutorials often demonstrate how to leverage existing web standards to support these new AI-driven capabilities.
Outside of his independent work at chan.dev, Chan is a member of the Developer Relations team at WorkOS. This position gives him a vantage point into how modern software companies handle infrastructure, identity, and the practical realities of shipping production code. This dual perspective—one foot in the enterprise world and the other in open-source education—allows him to address the specific challenges of security and reliability that often hinder the adoption of AI agents in professional environments.
Chan is a frequent contributor to GitHub under the handle @chantastic, where he maintains nearly 200 repositories. These range from personal site-building frameworks to experimental implementations of AI tools. His influence in the agent ecosystem is defined not by a single monolithic product, but by his role in shaping the standards and educational materials that allow other developers to build functional, interoperable agents. He is effectively building the standard library for the next generation of software interaction.
A technical educational platform focusing on React, component systems, and Model Context Protocol (MCP).
Strategic roadmap for pivoting from React educator to AI/Agent content creator. Comprehensive research, audience analysis, content strategy, and monetization plan for helping React developers learn AI agents. 19 documents, 100K+ words of planning.
Archived. Moved to https://github.com/chantastic/agents
⚠️ Archived — superseded by chantastic/agents
Opinionated Arch/Hyprland Setup
My Nix config
Cursed Mux for Web Dev Challenge
Chantastic (Michael Chan) is hiring
You've explored Chantastic (Michael Chan).
Join organizations building the agentic web.