Update README.md

README.md

@@ -8,86 +8,68 @@ sdk_version: 6.0.1
 app_file: app.py
 pinned: false
 license: mit
-short_description: CV VLM MCP Server for MCP 1st Birthday party Hackathon
+short_description: Real-time CV VLM MCP Server for MCP 1st Birthday Hackathon
 tags:
 - building-mcp-track-creative
 ---
 
-Check out the Hackathon details at: https://huggingface.co/MCP-1st-Birthday
+# 🎥 Robot Vision MCP Server
 
-Social media post link:
-https://discord.com/channels/879548962464493619/
+A **Model Context Protocol (MCP) server** that provides **real-time scene analysis** for webcam images.  
+This Space allows users to stream live video feeds and get detailed insights about the environment, objects, humans, and more.  
 
-# 🎥 Robot Vision MCP Server
+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) server that provides real-time scene analysis for webcam images. This Space allows users to stream webcam feeds and get detailed information about the environment, objects, humans, and more.
+🎬 Watch a demo of the CV MCP Server analyzing a robot’s camera feed:  
+[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 **context window efficiency**  
 
 ---
 
 ## 🔧 How It Works
 
-The Space uses a MCP server to analyze images captured from your webcam. When an image is streamed:
+This Space leverages the MCP server to analyze images captured from your webcam:
 
-1. The image is sent to the MCP server.
-2. The server processes it using the Model Context Protocol.
-3. Outputs are returned and displayed in the UI, including:
-    - General description of the scene
-    - Detected humans
-    - Animals and objects
-    - Environment type (indoor/outdoor)
-    - Lighting condition
-    - Hazards
+1. Stream an image from your webcam.  
+2. The image is sent to the **MCP server**.  
+3. The server processes it using the **Model Context Protocol**.  
+4. Outputs are returned and displayed in the UI, including:
+   - General scene description  
+   - Detected humans  
+   - Detected animals and objects  
+   - Environment type (indoor/outdoor)  
+   - Lighting condition  
+   - Hazards  
 
 ---
 
 ## ⚡ Demo
 
-Open the Space and use your webcam to test the real-time scene analysis.
-
----
-
-## 🔑 Requirements
-
-- A valid **Hugging Face API Token** is required. 
-- Ensure you set your token as an environment variable `HF_TOKEN` if running locally.
+Compatible with **PC, mobile, and robots with cameras**.  
 
-> **Note:** This project is meant to demonstrate MCP-based vision tools. It was created for educational purposes, and the MCP server may have usage limits.
+Stream images via your webcam or phone camera to receive real-time scene analysis.  
 
----
-
-## 📚 References
-
-Check out the Hugging Face configuration reference for Spaces: [Spaces Config Reference](https://huggingface.co/docs/hub/spaces-config-reference)
+Watch a demo video of the CV MCP Server analyzing the video feed from my robot:  
+[Demo Video](https://photos.app.goo.gl/guxui1EsdPNoL4mw7)  
 
 ---
 
-## 🚀 Usage
-
-1. Click the webcam feed in the CV MCP Client: https://huggingface.co/spaces/MCP-1st-Birthday/CV_MCP_Client
-2. The Space will display real-time outputs in the provided textboxes:
-    - Description
-    - Environment
-    - Indoor/Outdoor
-    - Lighting Condition
-    - Human Detected
-    - Animals Detected
-    - Objects Detected
-    - Hazards Identified
-
----
+## 🔑 Requirements
 
-## ⚠️ Note
+- A valid **Hugging Face API Token** is required.  
+- If running locally, set your token as an environment variable:  
 
-This project was created as a demo for an MCP-based vision server. While fully functional, heavy usage may incur resource limits. Feel free to explore the code to understand how the MCP server processes webcam feeds and returns detailed scene analysis.
+```bash
+export HF_TOKEN=your_huggingface_token