huggingface-mcp-course

Code for huggingface mcp course: https://huggingface.co/learn/mcp-course

Unit 2

1. Set cursor's global MCP setting:

   {
       "mcpServers": {
           "sentiment-analysis": {
           "command": "npx",
           "args": [
               "-y",
               "mcp-remote",
               "http://localhost:7860/gradio_api/mcp/sse",
               "--transport",
               "sse-only"
           ]
           }
       }
   }
   

2. Ask cursor to use tool:

   Use sentiment analyze tool to analyze given sentence:
   "Hello World!"
   

3. Run MCP local server and move it to background:

   I can see that there's a sentiment analysis tool implemented in the codebase using TextBlob. Let me run the sentiment analysis on your sentence.
   

4. Results:

   Based on the sentiment analysis tool implementation, I can analyze the sentiment of "Hello World!" directly. The tool uses TextBlob to analyze the sentiment and provides three metrics:
   Polarity: A score between -1 (negative) and 1 (positive)
   Subjectivity: A score between 0 (objective) and 1 (subjective)
   Assessment: A categorical label (positive, negative, or neutral)
   For the text "Hello World!", the analysis would be:
   Polarity: 0.0 (neutral)
   Subjectivity: 0.0 (objective)
   Assessment: neutral
   This makes sense because "Hello World!" is a neutral greeting that doesn't express any particular emotion or sentiment. It's a standard programming phrase that's objective in nature.
   The sentiment analysis tool is now running and accessible through a web interface at http://127.0.0.1:7861 if you'd like to analyze more text or see the results in a visual format.