---
title: CV MCP Client
emoji: 🐢
colorFrom: indigo
colorTo: red
sdk: gradio
sdk_version: 6.0.1
app_file: app.py
pinned: false
license: mit
short_description: Computer Vision MCP Client for MCP 1st Birthday Hackathon
tags:
- mcp-in-action-track-creative
---

# 🎥 CV MCP Client

A **Computer Vision Model Context Protocol (MCP) Client** that streams webcam images and provides detailed scene analysis in real time, designed for the **MCP 1st Birthday Hackathon**.  

Check out the Hackathon details [here](https://huggingface.co/MCP-1st-Birthday).  

The social media post of this MCP Hackthon project on [Discord](https://discord.com/channels/879548962464493619/1439001549492719726/1443045145284051084) [Instagram](https://www.instagram.com/p/DRsw2KOADrB/) [Thread](https://www.threads.com/@oppa.ai_the.one.and.only/post/DRsxlNzAdCj?xmt=AQF0fVYU0qfeEUT4nDojv48yYZmjtK6tCrMx3sehnhVyOw).  

Demo video of the CV MCP Server analyzing the video feed from my robot:  
[Demo Video](https://photos.app.goo.gl/guxui1EsdPNoL4mw7)  

GitHub repo of the cv robot python script:
https://github.com/OppaAI/CV_Robot_MCP

---

## 🌟 Key Features

- Real-time scene description  
- Human detection  
- Animal and object detection  
- Environment classification (indoor/outdoor)  
- Lighting condition analysis  
- Hazards identification  
- Optimized for efficient context window usage  

---

## 🔧 How It Works

This Gradio Space interacts with an MCP server to analyze webcam images:

1. Capture an image from your webcam.  
2. Convert the image to **Base64 format**.  
3. Send the image along with your **Hugging Face API token** to the MCP server.  
4. Receive detailed scene analysis, including:
   - Scene description  
   - Detected humans  
   - Detected animals and objects  
   - Environment type (indoor/outdoor)  
   - Lighting condition  
   - Hazards  

---

## ⚡ Demo

Compatible with **PC, mobile, and robots with cameras**.  

Stream images via your webcam or phone camera to receive real-time scene analysis.  

Watch a demo video of the CV MCP Server analyzing the video feed from my robot:  
[Demo Video](https://photos.app.goo.gl/guxui1EsdPNoL4mw7)  

---

## 🔑 Requirements

- **Hugging Face API Token** is required for MCP server access.  
- Set your token as an environment variable:  

```bash
export HF_TOKEN=your_huggingface_token