About Pokémon AI Demo
Pokémon AI Demo is a full-stack app for exploring and comparing Pokémon, finding counters, and generating teams. It serves players and agent integrations through a web interface and JSON API, with team suggestions generated from natural-language descriptions.
Key features
- 01View Pokémon stats and abilities
- 02Compare two Pokémon
- 03Find weaknesses and counters
- 04Generate teams from descriptions
Use cases
- 01Inspect a Pokémon’s moves and evolution
- 02Compare type advantages between Pokémon
- 03Find counters to a chosen Pokémon
- 04Create a team for a desired play style
MCP support
The README describes Django REST API endpoints for agent integration, but does not specify MCP protocol behavior.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEPokémon AI Demo
A full-stack application for exploring Pokémon data, comparing Pokémon, suggesting counters, and generating teams using AI. The system features a Django REST API backend and a React/MUI frontend.
Table of Contents
- System Setup and Deployment
- Available Modules and Their Use
- How to Use the Team Builder
- Web Interface Walkthrough
- Instructions for Agent Integration
System Setup and Deployment
Prerequisites
- Python 3.8+ (for backend)
- Node.js 16+ & npm (for frontend)
- pip (Python package manager)
Backend Setup (Django/DRF)
- Navigate to the backend directory:
cd mcp_server - Install dependencies:
pip install -r requirements.txt - Run migrations:
python manage.py migrate - Start the backend server:
The API will be available atpython manage.py runserverhttp://127.0.0.1:8000/api/.
Frontend Setup (React/MUI)
-
Navigate to the frontend directory:
cd mcp_frontend -
Install dependencies:
npm install npm install @mui/material @emotion/react @emotion/styled npm install @mui/icons-material -
Start the frontend server:
npm startThe app will be available at
http://localhost:5173/. -
Start the app automatically -
In terminal run command start.bat (for windows)
start.sh for (linux distro)
Environment Variables
- By default, the frontend expects the backend at
http://127.0.0.1:8000/api/agent/. AdjustAPI_BASEinmcp_frontend/src/App.jsxif needed.
dotenv structure (.env)
- make a .env file inside mcpserver folder
- contents - " POKE_API_URL = "https://pokeapi.co/api/v2/" GOOGLE_API_KEY = "your api key" "
Available Modules and Their Use
The backend exposes four main endpoints:
-
Pokémon Info (
POST /api/agent/pokemon-info/)- Input:
{ "name": "pikachu" } - Output: Basic info, stats, abilities, moves, evolution, and flavor text.
- Input:
-
Compare Pokémon (
POST /api/agent/compare/)- Input:
{ "pokemon1": "pikachu", "pokemon2": "bulbasaur" } - Output: Stat-by-stat comparison, type advantage, shared/unique abilities.
- Input:
-
Suggest Counters (
POST /api/agent/strategy/)- Input:
{ "name": "charizard" } - Output: Weaknesses and recommended counter Pokémon.
- Input:
-
Team Builder (
POST /api/agent/team/)- Input:
{ "description": "balanced team with fire and water types" } - Output: AI-generated team with roles and images.
- Input:
How to Use the Team Builder
- Purpose: Generate a Pokémon team based on a natural language description (e.g., "offensive team with good type coverage").
- How to Use:
- Go to the "Generate Team" section in the web UI.
- Enter your team description in the input field.
- Click "Generate".
- The AI will return a team of Pokémon, each with a name, role, and image.
- API Usage:
- Send a POST request to
/api/agent/team/with{ "description": "your team idea" }. - Receive a structured team suggestion in the response.
- Send a POST request to
Web Interface Walkthrough
The web app is organized into four main cards:
- Search for Pokémon
- Enter a Pokémon name to view its stats, types, abilities, moves, evolution chain, and flavor text.
- Compare Two Pokémon
- Enter two Pokémon names to compare their stats, type advantages, and abilities side-by-side.
- Suggest Counters
- Enter a Pokémon name to see its weaknesses and recommended counters.
- Generate Team
- Describe your desired team and get an AI-generated team with roles and images.
Each section provides instant feedback, loading indicators, and error messages for a smooth user experience.
Instructions for Agent Integration
You can integrate external agents or scripts with the backend API. Example usage:
- Python Example:
import requests response = requests.post('http://127.0.0.1:8000/api/agent/pokemon-info/', json={"name": "pikachu"}) print(response.json()) - Endpoints:
/api/agent/pokemon-info/(POST)/api/agent/compare/(POST)/api/agent/strategy/(POST)/api/agent/team/(POST)
- Request/Response Format: All endpoints accept and return JSON.
License
This project is for educational/demo purposes and is not affiliated with Nintendo, Game Freak, or The Pokémon Company.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.