MCP Needs a Browser
[Updated 2026-02-05] MCP isn’t the perfect protocol, but I’ll leave it to other people to complain about it. It has adoption and that is all that matters—our systems can be connected. Sometimes they are connected. But MCP tool use has not remotely broken into the mainstream. Why?
TL;DR: MCP’s consumer experience is broken—discovery, connection, and use all need browser-like simplicity. MCP Apps (ChatGPT Apps) are OpenAI’s first step toward that future.
The consumer experience around MCP is horrendous.
-
Discovery: Imagine your parents proactively and willingly taking on the task of “connecting to the Facebook MCP server”, even through relatively simple UIs. The act of searching and the subject of the search are essentially dealbreakers for non-technical users.
Even if users exceed the necessary technical bar, and even if users know exactly what they want done, they don’t know how to do it. They’re welcome to search the many lists of lists of lists of MCP servers, but it’s a lot of work and unlikely to surface trustworthy, stable results.
For real, production MCP use today, we essentially rely on developers to proactively integrate MCP servers in the background so we can unwittingly use these servers via the web servers of products we’re already using. Imagine being able to use any given website only after a Google engineer found time & motivation to integrate it into google.com.
- MCP needs a search engine & proactive connection embedded in the model.
-
Connection: Imagine if, every time you went to a website, you had to read a security notice, a privacy notice, approve a terms & conditions popup, and review the structure of JSON payloads the website will be making. This has become more true over time as a consumer (thanks, EU), but the actual browser-server connection itself remains virtually permission-less. MCP servers are servers, not client-side applications. Connecting to a server should be as easy as entering a URL in the browser.
Obviously, seamless MCP server connection has major security implications. The models & their MCP clients need to be architected to be more sandboxed and trust-less. Ultimately, the protection of the user & user data falls almost entirely within the purview of the model provider. They’ve got the users, the data, and the access to protect, and the new paradigms & architectures will have to flow from them.
- MCP needs to make connection more like a browser than an app store. This requires substantial protections built into the model.
-
Use: Imagine if, on a webpage, you had to manually trigger the correct sequence of API calls to deliver the proper user experience. With MCP, models are left with that impossible task. Invisible dependencies, edge cases, the permutations & combinatorics of all possible tool calls. Such a task is nontrivial even for relatively simple, newer products, let alone massive, complex, legacy systems and all of the unintuitive tech debt they’ve accrued.
Further, imagine if, in using a webpage, every input to and output from that page had to pass through a model. Would you use such a webpage to wire rent money? Models are non-deterministic. They can be wrong (less and less over time, but they always will). In most systems, there’s at least one action that you want to be direct-to-server and 100% deterministic.
- MCP needs to let server providers own parts of the client within the model.
All of the fundamental blockers to MCP have one thing in common: they’re totally dependent on the model provider to implement. Fortunately, OpenAI is on the right track.
MCP Apps (ChatGPT Apps) bring MCP one step closer to having a “browser”, but it doesn’t go all the way. I suspect that this is the direction that we’re heading. As with all macro trends, it will take us a while to get there.
MCP is very young, MCP Apps are younger, and the apps of today are only weeks old. Everything will get a LOT better. We’re building sunpeak to help. Sunpeak is the MCP App framework that helps developers quickstart, build, test, and ship MCP Apps and ChatGPT Apps. Please star us on Github!
Frequently Asked Questions
What is MCP and why does it matter?
MCP (Model Context Protocol) is the protocol that lets AI models interact with external systems. It enables tools, resources, and prompts to be shared between AI assistants and servers. MCP has adoption but hasn't reached mainstream consumers due to UX challenges.
Why hasn't MCP broken into mainstream consumer use?
MCP's consumer experience is broken in three areas: discovery (finding MCP servers is too technical for non-developers), connection (too many permissions and approvals required), and use (AI models struggle with complex sequences of tool calls).
What does MCP need to achieve mainstream adoption?
MCP needs three things: a search engine with proactive connection embedded in AI models, browser-like seamless connections with sandbox protections built into the model, and the ability for server providers to own parts of the client UI experience.
How do MCP Apps and ChatGPT Apps solve MCP's usability problems?
MCP Apps (also known as ChatGPT Apps) bring MCP closer to having a "browser" by letting server providers own parts of the client experience. They enable deterministic, direct-to-server UI interactions without everything passing through non-deterministic AI model inference.
What is the difference between MCP tools and MCP Apps?
MCP tools are API actions that AI models call non-deterministically. MCP Apps (ChatGPT Apps) add a visual UI layer (Resources) on top of MCP, letting users interact directly with deterministic interfaces while still leveraging AI for discovery and orchestration.
Will MCP and MCP Apps improve over time?
Yes. MCP is about a year old and MCP Apps (originally launched as ChatGPT Apps) debuted in October 2025. Both protocols will evolve significantly, especially as MCP moves from Anthropic to the Linux Foundation. Model providers will implement better discovery, connection, and use experiences.
What is sunpeak's role in the MCP ecosystem?
Sunpeak is the leading MCP App framework that helps developers build, test, and ship MCP Apps and ChatGPT Apps (which are MCP Resources with UI). It provides tools to create browser-like experiences within ChatGPT using the MCP protocol.
Why do MCP Apps need deterministic server interactions?
AI models are non-deterministic and can make mistakes. For critical actions like financial transactions, users need direct-to-server interactions that are 100% deterministic. MCP Apps (ChatGPT Apps) let server providers create these reliable UI experiences within ChatGPT.