Upskill your LLMs With Gradio MCP Servers

Upskill your LLMs With Gradio MCP Servers Have you ever wanted your favorite Large Language Model (LLM) to do more than just answer questions? What if it could edit images for you, browse the web, or organize your email inbox?

Well, now it can! In this blog post, I'll show you:

• What the MCP protocol is and how it works similarly to the smartphone apps we're all used to, but for LLMs.
• How you can find thousands of MCP servers via the "MCP App Store."
• How to add one of these servers to your favorite LLM of choice to grant it a new ability. We'll work through an example using Flux.1 Kontext[dev] which edits images from plain text instructions.

A Brief Intro To MCP

The Model Context Protocol (MCP) is an open standard that enables developers to build secure, two-way connections between an LLM and a set of tools. For example, if you create an MCP server that exposes a tool capable of transcribing a video, then you can connect an LLM client (such as Cursor, Claude Code, or Cline) to the server. The LLM will then know how to transcribe videos and use this tool for you depending on your request.

In short, an MCP server is a standard way to upskill your LLM by granting it a new ability. Think of it like the apps on your smartphone. On its own, your smartphone can't edit images, but you can download an app to do this from the app store. Now, if only there were an app store for MCP servers? 🤔

Hugging Face Spaces: The MCP App Store

Hugging Face Spaces is the world's largest collection of AI applications. Most of these spaces perform a specialized task with an AI model. For example:

• Image Background Removal
• OCR
• Text-to-Speech Synthesis

These spaces are implemented with Gradio, an open source python package for creating AI-powered web servers. As of version 5.28.0, Gradio apps support the MCP protocol.

That means that Hugging Face Spaces is the one place where you can find thousands of AI-powered abilities for your LLM, aka the MCP App Store!