FastAPI + MCP Server Integration with Gemini CLI

This project demonstrates how to build a FastAPI application, wrap it as an MCP (Model Context Protocol) Server, and integrate it with Gemini CLI for direct tool calling.

Project Structure

Features

FastAPI Application (sample_app.py)

• User Management: Create, read users with name, email, and age

• Task Management: Create, read, update, delete tasks

• Statistics: Get overview of users and tasks

• Health Check: Basic health monitoring endpoint

MCP Server (mcp_server.py)

• Tool Integration: Exposes all FastAPI endpoints as MCP tools

• Error Handling: Proper HTTP error handling and logging

• Type Safety: Full type annotations and schema validation

Available MCP Tools

1. get_app_info - Get basic app information

2. get_health - Check app health status

3. get_users - List all users

4. create_user - Create a new user

5. get_user - Get user by ID

6. get_tasks - List all tasks

7. create_task - Create a new task

8. get_task - Get task by ID

9. update_task - Update an existing task

10. delete_task - Delete a task

11. get_stats - Get user and task statistics

Quick Start

Option 1: Automated Demo

This interactive script will guide you through the entire setup and testing process.

Option 2: Manual Setup

1. Run Setup Script

2. Start the FastAPI Application

The FastAPI app will be available at http://localhost:8000

3. Start the MCP Server (in another terminal)

4. Install Gemini CLI

5. Add MCP Server to Gemini CLI

6. Test the Integration

Manual Setup

If you prefer to set up manually:

1. Install Python Dependencies

2. Start Services

• FastAPI app: python3 sample_app.py

• MCP server: python3 mcp_server.py

3. Install and Configure Gemini CLI

API Endpoints

The FastAPI application provides the following REST endpoints:

• GET / - App information

• GET /health - Health check

• GET /users - List users

• POST /users - Create user

• GET /users/{user_id} - Get user by ID

• GET /tasks - List tasks

• POST /tasks - Create task

• GET /tasks/{task_id} - Get task by ID

• PUT /tasks/{task_id} - Update task

• DELETE /tasks/{task_id} - Delete task

• GET /stats - Get statistics

MCP Tool Examples

Create and Manage Users

Create and Manage Tasks

Get Statistics

Troubleshooting

Common Issues

1. Port already in use: Make sure port 8000 is available for the FastAPI app

2. MCP server connection failed: Ensure the FastAPI app is running before starting the MCP server

3. Gemini CLI not found: Make sure Node.js and npm are installed, then install Gemini CLI globally

Debug Mode

To run the FastAPI app in debug mode:

Check MCP Server Status

Development

Adding New Endpoints

1. Add the endpoint to sample_app.py

2. Add the corresponding tool to mcp_server.py in the handle_list_tools() function

3. Add the tool handler in the handle_call_tool() function

Testing

You can test the FastAPI endpoints directly using curl:

License

This project is for educational purposes and demonstrates MCP integration patterns.