Update README.md

README.md

@@ -8,88 +8,67 @@ sdk_version: 6.0.1
 app_file: app.py
 pinned: false
 license: mit
-short_description: CV MCP Client with tags for MCP 1st Birthday party Hackathon
+short_description: Computer Vision MCP Client for MCP 1st Birthday Hackathon
 tags:
 - mcp-in-action-track-creative
 ---
 
-Check out the Hackathon details at: https://huggingface.co/MCP-1st-Birthday
+# 🎥 CV MCP Client
 
-Social media post link:
-https://discord.com/channels/879548962464493619/
+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**.  
 
-# 🎥 Computer Vision MCP Client
+Check out the Hackathon details [here](https://huggingface.co/MCP-1st-Birthday).  
+Join the community discussion on [Discord](https://discord.com/channels/879548962464493619/).  
 
-A Model Context Protocol (MCP) client that streams webcam images and retrieves detailed scene analysis from the MCP server.
+Demo video of the CV MCP Server analyzing the video feed from my robot:  
+[Demo Video](https://photos.app.goo.gl/guxui1EsdPNoL4mw7)  
 
 ---
 
-## 🌟 Features
+## 🌟 Key Features
 
-- Real-time scene description
-- Human detection
-- Animals and objects detection
-- Environment classification (indoor/outdoor)
-- Lighting condition analysis
-- Hazards identification
-- Optimized for context window efficiency
+- 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 uses a MCP server to analyze webcam images:
+This Gradio Space interacts with an MCP server to analyze webcam images:
 
-1. Capture an image via webcam.
-2. Convert the image to Base64 format.
-3. Send the image along with your Hugging Face token to the MCP server.
+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:
-    - Description of the scene
-    - Detected humans
-    - Animals and objects
-    - Environment type (indoor/outdoor)
-    - Lighting condition
-    - Hazards
+   - Scene description  
+   - Detected humans  
+   - Detected animals and objects  
+   - Environment type (indoor/outdoor)  
+   - Lighting condition  
+   - Hazards  
 
 ---
 
 ## ⚡ Demo
 
-Works on PC and phone, and robot with camera.
-Use your webcam/phone camera to stream images and receive real-time scene analysis.
+Compatible with **PC, mobile, and robots with cameras**.  
 
-Demo Video of using the CV MCP Server to analyze via the camera video feed of my robot:
-https://photos.app.goo.gl/guxui1EsdPNoL4mw7
+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 the MCP server to process images.
-- Set your token as an environment variable locally: `HF_TOKEN`.
-- Without a valid token, the app will display an error message.
+- **Hugging Face API Token** is required for MCP server access.  
+- Set your token as an environment variable:  
 
-> **Note:** This project uses a personal Hugging Face token for server access. Public users of the Space will be using your account, so be mindful of token usage limits.
-
----
-
-## 🚀 Usage
-
-1. Open the Space and allow webcam access.
-2. Stream images via the webcam.
-3. View the outputs in the textboxes:
-    - Description
-    - Environment
-    - Indoor/Outdoor
-    - Lighting Condition
-    - Human Detected
-    - Animals Detected
-    - Objects Detected
-    - Hazards Identified
-
----
-
-## ⚠️ Note
-
-This project demonstrates a client-side MCP integration. The token used in this Space is tied to the deployer's Hugging Face account. To avoid exposing your token to the public, consider using OAuth login so users can use their own Hugging Face tokens.
+```bash
+export HF_TOKEN=your_huggingface_token