FastAPI Hello World Application
@xxradar
About FastAPI Hello World Application
A test repository created using the GitHub MCP server
Basic information
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"mcp-fastapi-learning": {
"command": "python",
"args": [
"-m",
"venv",
"venv"
]
}
}
}Tools
No tools detected
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Overview
What is FastAPI Hello World Application?
A simple Hello World API built with FastAPI and MCP SSE support. It provides basic greeting endpoints, integrates with OpenAI’s GPT-4o for AI-powered chat completions, and includes automatic API documentation via Swagger UI and ReDoc.
How to use FastAPI Hello World Application?
Clone the repository, create a Python virtual environment, install dependencies from requirements.txt, then run with uvicorn main:app --reload or python main.py. Alternatively, build a Docker image and run the container on port 8000. Access endpoints via curl or browser, or connect to the MCP Inspector using npx @modelcontextprotocol/inspector.
Key features of FastAPI Hello World Application
- Root endpoint returning a Hello World message
- Dynamic greeting endpoint with a name parameter
- OpenAI GPT-4o integration for advanced chat completions
- Automatic API documentation (Swagger UI and ReDoc)
- MCP SSE support for Model Context Protocol
- Optional Docker containerized deployment
Use cases of FastAPI Hello World Application
- Quickly verify a FastAPI setup with a hello world response
- Generate personalized greetings via the
/hello/{name}endpoint - Test OpenAI chat completions with a custom prompt
- Explore automatic API documentation for development and testing
FAQ from FastAPI Hello World Application
What prerequisites are needed to run the application?
Python 3.7+ and pip are required for local setup. For the /openai endpoint, an OpenAI API key must be set as an environment variable. Docker is optional for containerized deployment.
How do I set the OpenAI API key?
Export the key as the OPENAI_API_KEY environment variable before running the application locally (export OPENAI_API_KEY=your_key_here). For Docker, pass it using -e OPENAI_API_KEY=your_key_here when running the container.
What endpoints does the application expose?
GET / (hello world), GET /hello/{name} (personalized greeting), GET /openai (chat completion with optional prompt parameter), GET /docs (Swagger UI), and GET /redoc (ReDoc documentation).
How can I access the API documentation?
Open /docs in your browser for Swagger UI, or /redoc for ReDoc.
How do I use the MCP SSE support?
Start the server and connect using the MCP Inspector by running npx @modelcontextprotocol/inspector in your terminal.
More Developer Tools MCP servers
MCP-Bridge
SecretiveShellA middleware to provide an openAI compatible endpoint that can call MCP tools
mcp-excalidraw
yctimlinMCP server and Claude Code skill for Excalidraw — programmatic canvas toolkit to create, edit, and export diagrams via AI agents with real-time canvas sync.
sentry-mcp
getsentryAn MCP server for interacting with Sentry via LLMs.
TalkToFigma
sonnylazuardiTalkToFigma: MCP integration between AI Agent (Cursor, Claude Code, Codex) and Figma, allowing Agentic AI to communicate with Figma for reading designs and modifying them programmatically.
MCP Framework
QuantGeekDevThe Typescript MCP Framework
Comments