About Model Context Protocol (MCP)
A demo project showing an SSE-based MCP server and client integrated with Google's Gemini. It also includes a FastAPI backend and a Streamlit interface for connecting to the server.
Key features
- 01SSE-based MCP server
- 02Optional SSE client
- 03Gemini integration
- 04FastAPI backend and Streamlit interface
Use cases
- 01Trying an MCP server and client with Gemini
- 02Connecting to an MCP server through a browser interface
MCP support
The project runs an MCP server over SSE and includes an optional SSE client that connects using the server URL.
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 READMEModel Context Protocol (MCP)
A working demo of MCP integrated with Google's Gemini.
🚀 Getting Started
1. Clone the repository
git clone https://github.com/drkhan107/mcp_gemini.git
cd your-repo-name
2. Set up environment variables
Create a .env file in the root directory and add your Google API key:
GOOGLE_API_KEY="your_api_key_here"
3. 📦 Install Dependencies
Install all required packages from requirements.txt:
pip install -r requirements.txt
4. 🖥️ Run the MCP Server
Start the MCP server:
python sse_server.py
✅ This will start the MCP server at the configured port (default is http://localhost:8080/sse).
5. 🧠 Start the MCP Client (Optional)
Once the server is running, start the SSE client with the server URL:
python ssc_client.py http://localhost:8080/sse
6. 🧠 Start the FastAPI server (To Use GUI)
Run the following command (To change the port etc, edit the fastapp.py file)
python fastapp.py
7. Launch Streamlit app
- Make sure MCP server is running (http://localhost:8080/sse)
- Make sure FastAPI is running.
Run the following command
streamlit run app.py
This will start the streamlit app on port 8501
8. Browser
Once you open the browser (localhost:8501), click on connect to MCP server.
✅ Done! You now have a working demo of the Model Context Protocol with Gemini.
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.