Are MCPs Overhyped? A Rant about MCPs — Henry Mao, Smithery

Hi, I'm Henry. Because MCP is such a new space, instead of going into technical details like most AI engineer videos that you're probably seeing, today I'll be doing a high-level overview and a rant about all the problems within the MCP space and ecosystem.

A quick introduction about myself: I'm Henry, I'm the founder and CEO of Smithery. I'm also a member of the MCP steering committee. Before Smithery, I co-founded Genie AI. Let me tell you a little bit about the origin story for Smithery.

This is around November last year, 2024. I went down this rabbit hole trying to figure out, trying to tackle the ARC AGI Challenge. And if you haven't heard of the ARC AGI Challenge, it's an IQ test made for LLMs.

And in this challenge, you're given two or three different examples of a pattern, and you want your LLM to predict the missing last pattern here. And it turns out that this challenge is very easy for humans to do.

Humans get about 80% accuracy on this challenge, but it's pretty hard for an LLM to do. And LLMs could not crack it for many, many years. So I kind of focused on tackling the challenge, but very quickly, OpenAI decided to release O3.

And O3 completely dominated the ARC AGI-1 Challenge and basically got human-level performance. It scored very well on math benchmarks as well. So we're basically done,right? AGI achieved. Autonomous agents are going to be solving all our problems now. But fast forward to 2025, and I'm wondering, where are all the autonomous agents?

Why are they not solving all the tasks that we don't want to be doing? So what we're seeing here is sort of Claude's paradox. We have all these frontier labs creating all this intelligence, but all this intelligence is stuck in a box.

And in order to make AI agents practically useful, we have to start thinking about context and capability. What are the inputs and outputs to our models? Everyone from startups to major labs recognizes this problem. And so in November 2024, Anthropic released the Model Context Protocol.

It's an open standard to help LLMs connect to different services, with a promise of standardizing this end-to-end problem. So when I saw MCPs in around this time last year, I was pretty excited about it. There was a small but vibrant developer community.

The models are getting smarter, and MCPs are standardizing the way models talk to services. So are we finally done? Well, not quite. With MCP and a new ecosystem of services trying to target AI agents, we have a bunch of new problems showing up.

So first, I want to go through the list of user problems that we have. So the first one is fragmentation. There are more and more MCP servers being deployed every single day, and it's becoming hard to find high-quality ones.

The MCP committee is currently working on a better solution for this by creating an official registry, thanks to Tess and the Pulse MCP team. Simply having a registry doesn't solve the problem. For example, how do we assign reputation to high-quality MCPs is still an open question.

Another problem that MCP users face is high-friction install. If you go to any MCP's GitHub repository, you'll probably see this five-step installation process, which makes it very difficult to install. And in addition to that, once you have your MCP installed, you might just have installed an insecure, unsecured MCP.

Finally, it's unclear how we're going to create this new economy of AI-native services if we don't have a plan on how to handle agentic payments. Open questions in this area include: how do I get agents to pay on my behalf?

And how do I avoid subscribing to 100 different services, each charging $10 a month? Next, let's look at the developer-side problems. So if you're building an MCP, you probably face hosting problems. Thanks to the Spring Board HTTP transport, it's now much easier for developers to find platforms to host on.

But hosting is still a challenge. Developers will have to deal with stateful sessions, resumability, and other issues. The developer tooling is also quite lacking in the MCP space. We have a basic MCP inspector provided by the official MCP repository, which allows you to test out different tools, check out your prompts.

But there are still open questions that developers are asking us. For example, how do I design the best MCPs? How do I know if my tool is going to be called? How do I create the best agent experience?

Next, we also have distribution as a problem. If you're a developer, you create an MCP. How does your MCP get discovered? Observability is also an issue. If you deploy your MCP and people are using it, how do you improve this MCP once it's launched?

And lastly, how do you make money out of your MCPs? So in summary, the MCP ecosystem is very exciting, but it has a bunch of different problems. On the left side, we have all the problems faced by MCP users.

On theright side, we have problems faced by all the MCP developers. That's why we're building Smithery. I started Smithery in around December 2024 to tackle these challenges. Smithery is aiming to become the AI gateway to grow and orchestrate this new era of AI-native services for AI agents.

So far, we've only scratched the surface of the problems I've described previously. But we built this little demo to showcase what you can build when some of these problems are solved. So here what you're seeing is the Smithery playground.

The main goal of the playground is for us to demonstrate what an AI agent can do when it has access to thousands of curated MCPs. So let's start with a prompt. Find the most pressing issue on my GitHub repository called smithery-ai/cli and create a new ticket on Linear.

Okay, so let's submit this prompt. You'll see the agent first start thinking about the issue. It then calls this search servers function, which looks up for all the servers within Smithery. It connects to the best server.

It also connects to Linear. It's able to go on GitHub using the GitHub MCP to find different bugs. It's trying to find the most high-priority item.

So it found a team, and now it's creating a ticket on Linear.

Great. So it looks like our agent has successfully gone on GitHub, looked for the most pressing issue on my GitHub issues, and created a Linear ticket. So let's take a look at this ticket. Nice. Okay, so it has a lot of details.

It has even a link to the original issue. Yeah, so we have sort of an end-to-end task being solved by an AI agent connected to two different MCPs. So obviously, this demo only scratches the surface, but you can imagine what we can do when more and more servers get deployed on Smithery.

So this graph kind of shows you the number of servers being deployed over the last couple of months and the number of tool calls we've been getting. With all this developer enthusiasm, I'm confident that we can solve all of the problems that I mentioned in this talk today.

It's clear to me that the future of the internet will be dominated by tool calls rather than clicks. And in this new world, it's going to be the agent experience that matters more than the user experience. And this agent experience is not going to be built by just me or a few companies.

It's going to be built by all of you. Thank you.