MCP Chatbot

MCP Chat Backend

This project is a serverless FastAPI backend for a chatbot that generates and executes SQL queries on a Postgres database using OpenAI's GPT models, then returns structured, UI-friendly responses. It is designed to run on AWS Lambda via AWS SAM, but can also be run locally or in Docker.

Features

FastAPI REST API with a single /ask endpoint
Uses OpenAI GPT models to generate and summarize SQL queries
Connects to a Postgres (Supabase) database
Returns structured JSON responses for easy frontend rendering
CORS enabled for frontend integration
Deployable to AWS Lambda (SAM), or run locally/Docker
Verbose logging for debugging (CloudWatch)

Project Structure

├── main.py            # Main FastAPI app and Lambda handler
├── requirements.txt   # Python dependencies
├── template.yaml      # AWS SAM template for Lambda deployment
├── samconfig.toml     # AWS SAM deployment config
├── Dockerfile         # For local/Docker deployment
├── .gitignore         # Files to ignore in git
└── .env               # (Not committed) Environment variables

Setup

1. Clone the repository

git clone <your-repo-url>
cd mcp-chat-3

2. Install Python dependencies

python -m venv .venv
source .venv/bin/activate  # or .venv\Scripts\activate on Windows
pip install -r requirements.txt

3. Set up environment variables

Create a .env file (not committed to git):

OPENAI_API_KEY=your-openai-key
SUPABASE_DB_NAME=your-db
SUPABASE_DB_USER=your-user
SUPABASE_DB_PASSWORD=your-password
SUPABASE_DB_HOST=your-host
SUPABASE_DB_PORT=your-port

Running Locally

With Uvicorn

uvicorn main:app --reload --port 8080

With Docker

docker build -t mcp-chat-backend .
docker run -p 8080:8080 --env-file .env mcp-chat-backend

Deploying to AWS Lambda (SAM)

Install AWS SAM CLI
Build and deploy:

sam build
sam deploy --guided

Configure environment variables in template.yaml or via the AWS Console.
The API will be available at the endpoint shown after deployment (e.g. https://xxxxxx.execute-api.region.amazonaws.com/Prod/ask).

API Usage

POST /ask

Body: { "question": "your question here" }
Response: Structured JSON for chatbot UI, e.g.

{
  "messages": [
    {
      "type": "text",
      "content": "Sample 588 has a resistance of 1.2 ohms.",
      "entity": {
        "entity_type": "sample",
        "id": "588"
      }
    },
    {
      "type": "list",
      "items": ["Item 1", "Item 2"]
    }
  ]
}

See main.py for the full schema and more details.

Environment Variables

OPENAI_API_KEY: Your OpenAI API key
SUPABASE_DB_NAME, SUPABASE_DB_USER, SUPABASE_DB_PASSWORD, SUPABASE_DB_HOST, SUPABASE_DB_PORT: Your Postgres database credentials

Development Notes

All logs are sent to stdout (and CloudWatch on Lambda)
CORS is enabled for all origins by default
The backend expects the frontend to handle the structured response format

License

MIT (or your license here)

This server cannot be installed

security - not tested

license - not found

quality - not tested

How are these scores calculated?

hybrid server

The server is able to function both locally and remotely, depending on the configuration or use case.

A serverless backend that enables natural language querying of a Postgres database, converting user questions into SQL and returning structured, UI-friendly responses.

Related MCP Servers

Model Context Protocol PostgreSQL Server
endaoment
-
security
F
license
-
quality
A server that allows AI models to interact with PostgreSQL databases through a standardized protocol, providing database schema information and SQL query execution capabilities.
Last updated -
1
JavaScript
Langflow Document Q&A Server
GongRzhe
A
security
A
license
A
quality
Enables querying documents through a Langflow backend using natural language questions, providing an interface to interact with Langflow document Q\&A flows.
Last updated -
1
14
JavaScript
MIT License
SQL Query MCP Server
rajeevchandra
-
security
F
license
-
quality
A FastMCP server that enables natural language querying of PostgreSQL databases through LLM integration, allowing users to generate SQL queries from plain English and visualize the results.
Last updated -
2
Python
NLSQL MCP Server
tushar-badhwar
-
security
A
license
-
quality
A Node.js package that provides a Model Context Protocol server for converting natural language questions into SQL queries using AI-powered multi-agent systems.
Last updated -
3
1
Python
MIT License

View all related MCP servers