Flight Search Assistant (Powered by Gemini + MCP)
LocalAbout Flight Search Assistant (Powered by Gemini + MCP)
A Streamlit flight-search app that uses Gemini to interpret natural-language queries and fetch real-time flight information through an MCP backend. It is for people who want to search for flights conversationally and view formatted results in an interactive interface.
Key features
- 01Natural-language flight search
- 02Fetch live flight data through MCP
- 03Gemini interprets queries and selects tools
- 04Interactive Streamlit interface
- 05Format results and handle errors
Use cases
- 01Search flights by origin, destination, and date
- 02Review live flight search results in the interface
MCP support
The app invokes tools from the `mcp-flight-search` backend, which retrieves flight information through the SERP API for display in the interface.
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 README✈️ Flight Search Assistant (Powered by Gemini + MCP)
This is a simple and powerful Streamlit-based flight search tool that uses Google's Gemini AI model and MCP (Model Context Protocol) Server to find real-time flight information using natural language queries.
Users can search for flights like:
"Find flights from Atlanta to Las Vegas on 2025-05-05"
Gemini interprets the query, identifies the right function/tool to use, and fetches flight data from the mcp-flight-search backend.
🔧 Features
- ✅ Natural language flight search
- ✅ Real-time flight data (via SERP API through MCP)
- ✅ Gemini Pro 2.5 model for query understanding
- ✅ Interactive UI using Streamlit
- ✅ Cleanly formatted flight results
- ✅ Error handling and fallback messaging
📦 Setup Instructions
1. Clone the repo
git clone https://github.com/parth-patel97/mcp-server-gemini.git
cd mcp-server-gemini
2. Install dependencies
pip install -r requirements.txt
3. Create a .env file
Create a .env file in the root of your project:
GEMINI_API_KEY=your-gemini-api-key
SERP_API_KEY=your-serp-api-key
The app will automatically load these using python-dotenv.
4. Run the app
streamlit run flight_search_ui.py
🖼 Sample Screenshot
🔁 Flow Diagram
🧠 How it Works
- User enters a natural language query.
- Streamlit sends the query to Gemini 2.5.
- Gemini interprets the query and generates a function call (tool use).
- The tool is executed via MCP Server (
mcp-flight-search) which fetches data from SERP API. - The response is formatted and shown in the Streamlit UI.
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.