Language Learning MCP Server for Puch AI
This is a starter template for creating your own Model Context Protocol (MCP) server that works with Puch AI. It comes with ready-to-use tools for language learning and image processing.
What is MCP?
MCP (Model Context Protocol) allows AI assistants like Puch to connect to external tools and data sources safely. Think of it like giving your AI extra superpowers without compromising security.
What's Included in This Starter?
🌍 Language Learning Assistant Tool
- Translation help - Translate text between languages with grammar explanations
- Grammar explanations - Get detailed explanations of grammar rules and concepts
- Practice exercises - Receive customized practice exercises for different skill levels
- Learning resources - Find recommended apps, websites, and study materials
🃏 Vocabulary Practice Tool
- Flashcards - Create vocabulary flashcards for any language and category
- Quizzes - Generate vocabulary quizzes to test your knowledge
- Word lists - Get organized word lists by category and difficulty
- Fill-in-the-blank exercises - Practice with interactive exercises
🖼️ Image Processing Tool
- Convert images to black & white - Upload any image and get a monochrome version
🔐 Built-in Authentication
- Bearer token authentication (required by Puch AI)
- Validation tool that returns your phone number
Quick Setup Guide
Step 1: Install Dependencies
First, make sure you have Python 3.11 or higher installed. Then:
# Create virtual environment
uv venv
# Install all required packages
uv sync
# Activate the environment
source .venv/bin/activate
Step 2: Set Up Environment Variables
Create a .env file in the project root:
# Copy the example file
cp .env.example .env
Then edit .env and add your details:
AUTH_TOKEN=your_secret_token_here
MY_NUMBER=919876543210
Important Notes:
AUTH_TOKEN: This is your secret token for authentication. Keep it safe!MY_NUMBER: Your WhatsApp number in format{country_code}{number}(e.g.,919876543210for +91-9876543210)
Step 3: Run the Server
cd mcp-bearer-token
python mcp_starter.py
You'll see: 🚀 Starting MCP server on http://0.0.0.0:8086
Step 4: Make It Public (Required by Puch)
Since Puch needs to access your server over HTTPS, you need to expose your local server:
Option A: Using ngrok (Recommended)
-
Install ngrok: Download from https://ngrok.com/download
-
Get your authtoken:
- Go to https://dashboard.ngrok.com/get-started/your-authtoken
- Copy your authtoken
- Run:
ngrok config add-authtoken YOUR_AUTHTOKEN
-
Start the tunnel:
ngrok http 8086
Option B: Deploy to Cloud
You can also deploy this to services like:
- Railway
- Render
- Heroku
- DigitalOcean App Platform
How to Connect with Puch AI
- Open Puch AI in your browser
- Start a new conversation
- Use the connect command:
/mcp connect https://your-domain.ngrok.app/mcp your_secret_token_here
Debug Mode
To get more detailed error messages:
/mcp diagnostics-level debug
Customizing the Starter
Adding New Tools
-
Create a new tool function:
@mcp.tool(description="Your tool description") async def your_tool_name( parameter: Annotated[str, Field(description="Parameter description")] ) -> str: # Your tool logic here return "Tool result" -
Add required imports if needed
Example Language Learning Queries
You can ask Puch to:
- "Translate 'Hello, how are you?' to Spanish"
- "Explain past tense in French"
- "Give me a vocabulary quiz for Japanese beginners"
- "Create flashcards for food vocabulary in Italian"
- "Find resources to learn German"
- "Give me a practice exercise for intermediate Spanish"
📚 Additional Documentation Resources
Official Puch AI MCP Documentation
- Main Documentation: https://puch.ai/mcp
- Protocol Compatibility: Core MCP specification with Bearer & OAuth support
- Command Reference: Complete MCP command documentation
- Server Requirements: Tool registration, validation, HTTPS requirements
Technical Specifications
- JSON-RPC 2.0 Specification: https://www.jsonrpc.org/specification (for error handling)
- MCP Protocol: Core protocol messages, tool definitions, authentication
Supported vs Unsupported Features
✓ Supported:
- Core protocol messages
- Tool definitions and calls
- Authentication (Bearer & OAuth)
- Error handling
✗ Not Supported:
- Videos extension
- Resources extension
- Prompts extension
Getting Help
- Join Puch AI Discord: https://discord.gg/VMCnMvYx
- Check Puch AI MCP docs: https://puch.ai/mcp
- Puch WhatsApp Number: +91 99988 81729
Happy language learning! 🌍
Use the hashtag #BuildWithPuch in your posts about your MCP!
This starter makes it super easy to create your own language learning MCP server for Puch AI. Just follow the setup steps and you'll be ready to help users learn new languages with your custom tools!