← back
Are MCPs Overhyped? A Rant about MCPs — Henry Mao, Smithery
Original: Are MCPs Overhyped? A Rant about MCPs — Henry Mao, Smithery
Takeaway
MCP solves LLM-service connectivity but reputation, install friction, monetization, and discovery remain — Smithery aims to be the AI gateway for that ecosystem.
Summary
- Henry Mao (Smithery CEO, MCP steering committee) frames MCP as a response to 'Claude's paradox' — frontier intelligence stuck in a box without context/capability access.
- User-side problems: server fragmentation, no reputation system, 5-step GitHub installs, security risks, no agentic payments story.
- Developer-side problems: hosting (Streamable HTTP helps), inadequate tooling beyond MCP Inspector, discovery, observability, and monetization.
- Demo: Smithery playground search_servers function dynamically connects to GitHub and Linear MCPs to find a top issue and file a ticket end-to-end.
- Predicts the future internet will be dominated by tool calls (agent experience) over clicks (user experience).
mcpagentsecosystem
Original description
AI agents are becoming smarter but lack the broad capability to take action in practice. At Smithery, we believe the missing link is an AI orchestration layer—a unified interface that gives agents context, action, and a way to learn from real interactions. This talk explores the problem space in the Model Context Protocol (MCP) ecosystem and how we're tackling it at Smithery.