🧠 Rick and Morty API MCP

This is a small AI-powered FastAPI project that interacts with the Rick and Morty API, designed to process free-form user text (like "Tell me about an episode with Blips") and extract meaningful queries using an MCP-style endpoint (Model Context Protocol).

📚 Built as part of my personal learning journey into Python, AI agent architecture, and API design.
🧑‍💻 GitHub: unix14

---

---

🚀 Features

• 🔍 Free-text AI endpoint (/mcp) for extracting intent and arguments from natural language.
• 🎥 Filters episodes by name keywords and returns air dates in a friendly format.
• 👤 (WIP) Character search functionality.
• 📦 Cleanly loads secrets (e.g., API keys) from .env using a separate config file.
• ⚡ Uses FastAPI and httpx for async performance.

---

Live Preview

You can access a live preview of the Rick and Morty MCP Server running here.

Feel free to test the API and explore its features through this URL.

---

🧪 Example

Request:

POST /mcp
{
  "messages": [
    { "role": "user", "content": "Give me details about an episode with something like Rixty" }
  ],
  "data_requests": [
    {
      "name": "get_episodes_by_name",
      "arguments": { "name_keyword": "Rixty" }
    }
  ]
}

Response:

{
  "S01E08: Rixty Minutes was aired in 17.03.2014"
}

---

🛠 Tech Stack

• Python 3.11+
• FastAPI
• httpx (async HTTP client)
• python-dotenv
• Uvicorn

---

📁 Project Structure

rick-and-morty-api-mcp/
├── main.py        # FastAPI app with /mcp endpoint
├── config.py      # Loads API keys and env variables
├── .env           # Local secret store
├── test_*.py      # Simple test scripts
└── README.md

---

🔐 Environment Setup

Create a .env file in the root:

MY_API_KEY=your-key-here

Then in config.py, it's loaded like this:

from dotenv import load_dotenv
import os

load_dotenv()
API_KEY = os.getenv("MY_API_KEY")

---

▶️ Running the Server

pip install -r requirements.txt
uvicorn main:app --reload

Test it on: http://localhost:8000/docs

---

📈 Motivation

I built this project as part of my self-guided study in:

• Natural Language to structured data pipelines
• AI-oriented API architecture (MCP-style thinking)
• Async APIs and Python backend development

It’s a stepping stone towards building intelligent agents that understand human intent through structured context.

---

🧠 Future Ideas

• Integrate OpenAI or LLMs to automatically convert user messages to data_requests
• Add more endpoint support (characters, locations, episodes, etc.)
• Improve fuzzy matching and scoring on episode names
• Add a simple front-end for fun!

---

📫 Contact

If you're curious about this, feel free to reach out via GitHub: github.com/unix14