mcp-db-server
An MCP (Model Context Protocol) server that exposes relational databases (PostgreSQL/MySQL) to AI agents with natural language query support. Transform natural language questions into SQL queries and get structured results.
Features
- Multi-Database Support: Works with PostgreSQL and MySQL
- Natural Language to SQL: Convert plain English queries to SQL using HuggingFace transformers
- RESTful API: Clean FastAPI-based endpoints for database operations
- Safety First: Read-only operations with query validation and result limits
- Docker Ready: Complete containerization with Docker Compose
- Production Ready: Health checks, logging, and error handling
- AI Agent Friendly: Designed specifically for AI agent integration
Version 1.4.0 Changes
- Added mandatory
X-API-Keyauthentication for all database HTTP endpoints;/healthremains public for health checks. - Removed unrestricted credentialed CORS and made allowed origins explicitly configurable.
- Changed the default HTTP bind address to
127.0.0.1. - Added table-name validation against existing database tables to block SQL injection through table routes.
- Added PostgreSQL
sslmode=requirecompatibility forasyncpgconnections. - Updated Docker Compose, environment examples, and documentation for secure API-key configuration.
- Published Docker images:
souhardyak/mcp-db-server:1.4.0souhardyak/mcp-db-server:latest
- Added GitHub Container Registry publishing for:
ghcr.io/souhar-dya/mcp-db-server:1.4.0ghcr.io/souhar-dya/mcp-db-server:latest
API Endpoints
Quick Start
Option 1: Docker Compose (Recommended)
-
Clone and start the services:
git clone https://github.com/Souhar-dya/mcp-db-server.git cd mcp-db-server export MCP_API_KEY="$(openssl rand -hex 32)" docker-compose up --build -
Test the endpoints:
# Health check curl http://localhost:8000/health # List tables (requires the configured API key) curl -H "X-API-Key: $MCP_API_KEY" http://localhost:8000/mcp/list_tables # Describe a table curl -H "X-API-Key: $MCP_API_KEY" http://localhost:8000/mcp/describe/customers # Natural language query curl -X POST "http://localhost:8000/mcp/query" \ -H "X-API-Key: $MCP_API_KEY" \ -H "Content-Type: application/json" \ -d '{"nl_query": "show top 5 customers by total orders"}'
Option 2: Local Development
-
Prerequisites:
- Python 3.11+
- PostgreSQL or MySQL database
-
Install dependencies:
pip install -r requirements.txt -
Set environment variables:
export DATABASE_URL="postgresql+asyncpg://user:password@localhost:5432/dbname" export MCP_API_KEY="$(openssl rand -hex 32)" # or for MySQL: # export DATABASE_URL="mysql+pymysql://user:password@localhost:3306/dbname" -
Run the server:
python -m app.server
Sample Database
The project includes a sample database with realistic e-commerce data:
- customers: Customer information (10 sample customers)
- orders: Order records (17 sample orders)
- order_items: Individual items within orders
- order_summary: View combining order and customer data
Natural Language Query Examples
The server can understand various types of natural language queries:
# Get all customers
curl -X POST "http://localhost:8000/mcp/query" \
-H "Content-Type: application/json" \
-d '{"nl_query": "show all customers"}'
# Count orders by status
curl -X POST "http://localhost:8000/mcp/query" \
-H "Content-Type: application/json" \
-d '{"nl_query": "count orders by status"}'
# Top customers by order value
curl -X POST "http://localhost:8000/mcp/query" \
-H "Content-Type: application/json" \
-d '{"nl_query": "top 5 customers by total order amount"}'
# Recent orders
curl -X POST "http://localhost:8000/mcp/query" \
-H "Content-Type: application/json" \
-d '{"nl_query": "show recent orders from last week"}'
Configuration
Environment Variables
Database Connection Examples
# PostgreSQL
DATABASE_URL=postgresql+asyncpg://user:pass@localhost:5432/mydb
# MySQL
DATABASE_URL=mysql+pymysql://user:pass@localhost:3306/mydb
# PostgreSQL with SSL
DATABASE_URL=postgresql+asyncpg://user:pass@localhost:5432/mydb?sslmode=require
### Database Connection Examples
```bash
# PostgreSQL (local or cloud)
DATABASE_URL=postgresql+asyncpg://user:password@host:5432/dbname
# MySQL (local or cloud)
DATABASE_URL=mysql+aiomysql://user:password@host:3306/dbname
# PostgreSQL with SSL (cloud, e.g. Neon, Supabase, Aiven)
DATABASE_URL=postgresql+asyncpg://user:password@host:5432/dbname?sslmode=require
# MySQL with SSL (cloud, e.g. Aiven, PlanetScale)
DATABASE_URL=mysql+aiomysql://user:password@host:3306/dbname?ssl-mode=REQUIRED
Note:
- For MySQL cloud providers, the
ssl-modeparameter in the URL is ignored by the driver, but SSL is always enabled in the MCP server for cloud connections.- For PostgreSQL, use
sslmode=requirefor cloud DBs. For MySQL, just use the standard URL; SSL is handled automatically.- If you see errors about
ssl-modeorsslmode, check your URL and ensure you are using the correct driver prefix (mysql+aiomysqlorpostgresql+asyncpg).
Cloud Database Examples
# Neon (PostgreSQL)
DATABASE_URL=postgresql+asyncpg://username:[email protected]/dbname
# Aiven (MySQL)
DATABASE_URL=mysql+aiomysql://avnadmin:[email protected]:11079/defaultdb?ssl-mode=REQUIRED
Docker Usage with Cloud DB
docker run -d \
-p 8000:8000 \
-e DATABASE_URL="<your_cloud_database_url>" \
-e MCP_API_KEY="<your_random_api_key>" \
souhardyak/mcp-db-server:latest
GitHub Container Registry is also available:
docker login ghcr.io
docker pull ghcr.io/souhar-dya/mcp-db-server:latest
docker run -d \
-p 8000:8000 \
-e DATABASE_URL="<your_database_url>" \
-e MCP_API_KEY="$MCP_API_KEY" \
ghcr.io/souhar-dya/mcp-db-server:latest
Images are published automatically when a v*.*.* tag is pushed. The workflow also creates the matching GitHub Release. To publish an existing tag such as v1.4.0, open the workflow's Run workflow action and enter 1.4.0. Set the GHCR package visibility to Public in the repository's Packages settings if unauthenticated pulls should be allowed.
Troubleshooting
- If you get
connect() got an unexpected keyword argument 'ssl-mode', ignore it: SSL is still enabled. - For network errors, check firewall and DB credentials.
- For MySQL, always use
mysql+aiomysqlin the URL for async support.
### PostgreSQL SSL connection note
For PostgreSQL cloud providers, use an asyncpg URL and `sslmode=require`:
```bash
DATABASE_URL=postgresql+asyncpg://user:password@host:5432/dbname?sslmode=require
The server normalizes sslmode=require to the ssl option expected by asyncpg. A temporary PostgreSQL verification was completed successfully against a compatible cloud database using CREATE, INSERT, SELECT, UPDATE, DELETE, and DROP; no test data was retained. Never commit or share a connection URL containing a real password.
API key authentication
MCP_API_KEY is a secret that you generate and provide to the server. It protects all database HTTP endpoints through the X-API-Key request header. The /health endpoint remains public for container health checks.
Generate a strong key on Linux or macOS:
export MCP_API_KEY="$(openssl rand -hex 32)"
Generate one in Windows PowerShell:
$bytes = New-Object byte[] 32
[Security.Cryptography.RandomNumberGenerator]::Create().GetBytes($bytes)
$env:MCP_API_KEY = ([BitConverter]::ToString($bytes) -replace "-", "").ToLower()
Start the Docker image with the key:
docker run -d \
-p 8000:8000 \
-e DATABASE_URL="<your_database_url>" \
-e MCP_API_KEY="$MCP_API_KEY" \
souhardyak/mcp-db-server:latest
Call a protected endpoint with the same key:
curl -H "X-API-Key: $MCP_API_KEY" http://localhost:8000/mcp/list_tables
Keep the key in a password manager or deployment secret store. Do not commit it to Git, put it in a public image, or include it in logs.
Security Features
- Mandatory HTTP Authentication: Database API routes require
X-API-Key;/healthremains public for health checks - Secure Network Default: HTTP mode binds to
127.0.0.1unless explicitly configured otherwise - Restricted CORS: Cross-origin access is disabled unless origins are explicitly configured
- Read-Only Operations: Only SELECT queries are allowed
- Query Validation: Automatic detection and blocking of dangerous SQL operations
- Result Limiting: Maximum 50 rows per query (configurable)
- Input Sanitization: Protection against SQL injection
- Safe Defaults: Secure configuration out of the box
Architecture
mcp-db-server/
├── app/
│ ├── __init__.py # Package initialization
│ ├── server.py # FastAPI application and endpoints
│ ├── db.py # Database connection and operations
│ └── nl_to_sql.py # Natural language to SQL conversion
├── .github/workflows/
│ └── docker-publish.yml # CI/CD pipeline
├── docker-compose.yml # Docker Compose configuration
├── Dockerfile # Container definition
├── init_db.sql # Sample database schema and data
├── requirements.txt # Python dependencies
└── README.md # This file
Model Context Protocol (MCP) Integration
This server is designed to work seamlessly with MCP-compatible AI agents:
- Standardized Endpoints: RESTful API following MCP conventions
- Structured Responses: JSON responses optimized for AI consumption
- Error Handling: Consistent error messages and status codes
- Documentation: OpenAPI/Swagger documentation available at
/docs
Publish To VS Code MCP Store (Registry)
VS Code MCP gallery uses MCP Registry metadata. This repository now includes
server.json for registry publication.
1) Build and publish Docker image
docker build -t souhardyak/mcp-db-server:1.3.1 .
docker push souhardyak/mcp-db-server:1.3.1
2) Validate server metadata
server.json is configured for an OCI package and stdio transport:
name:io.github.Souhar-dya/mcp-db-serverregistryType:ociidentifier:docker.io/souhardyak/mcp-db-server:1.3.1
The Dockerfile includes registry ownership annotation:
io.modelcontextprotocol.server.name=io.github.Souhar-dya/mcp-db-server
3) Publish to MCP Registry
Install publisher and publish metadata:
mcp-publisher login github
mcp-publisher publish
After publishing, users can discover/install it from MCP-compatible clients, including VS Code MCP experiences that read from the registry.
4) Local VS Code config example
{
"servers": {
"mcp-db-server": {
"type": "stdio",
"command": "docker",
"args": [
"run",
"--rm",
"-i",
"-e",
"DATABASE_URL=sqlite+aiosqlite:////data/default.db",
"souhardyak/mcp-db-server:1.3.1"
]
}
}
}
Docker Smoke Test
Use the dedicated Docker smoke test in tests/docker:
python tests/docker/smoke_test.py
This verifies Docker daemon access, image build, container startup, and health status.
Deployment
Docker Hub
# Pull the latest image
docker pull souhardyak/mcp-db-server:latest
# Run with your database
docker run -d \
-p 8000:8000 \
-e DATABASE_URL="your_database_url_here" \
souhardyak/mcp-db-server:latest
Kubernetes
apiVersion: apps/v1
kind: Deployment
metadata:
name: mcp-db-server
spec:
replicas: 3
selector:
matchLabels:
app: mcp-db-server
template:
metadata:
labels:
app: mcp-db-server
spec:
containers:
- name: mcp-db-server
image: souhardyak/mcp-db-server:latest
ports:
- containerPort: 8000
env:
- name: DATABASE_URL
valueFrom:
secretKeyRef:
name: db-secret
key: url
---
apiVersion: v1
kind: Service
metadata:
name: mcp-db-server-service
spec:
selector:
app: mcp-db-server
ports:
- port: 80
targetPort: 8000
type: LoadBalancer
Testing
Run Tests Locally
# Start test database
docker-compose up postgres -d
# Wait for database to be ready
sleep 10
# Run tests
python -m pytest tests/ -v
Manual Testing
# Test health endpoint
curl http://localhost:8000/health
# Test table listing
curl http://localhost:8000/mcp/list_tables
# Test natural language query
curl -X POST "http://localhost:8000/mcp/query" \
-H "Content-Type: application/json" \
-d '{"nl_query": "show me all customers from California"}'
Contributing
- Fork the repository
- Create your feature branch (
git checkout -b feature/amazing-feature) - Commit your changes (
git commit -m 'Add some amazing feature') - Push to the branch (
git push origin feature/amazing-feature) - Open a Pull Request
License
This project is licensed under the Apache License 2.0 - see the LICENSE file for details.
📝 Changelog
v1.3.0 (2025-12-24) - Docker Path Fix
- Fixed: Resolved import path issues in Docker container causing
from db import DatabaseManagerto fail - Fixed: Changed relative paths to absolute paths in Dockerfile and docker-compose.yml healthchecks
- Improved:
mcp_server.pynow uses robust path resolution that works both locally and in Docker containers - Updated: Docker image rebuilt and pushed with all path fixes
v1.2.0 (2025-11-03) - MySQL Column Access Fix
- Fixed: Resolved
Could not locate column in row for column 'column_name'error with MySQL databases - Fixed: Changed
describe_tablemethod to use index-based row access for better SQLAlchemy compatibility - Improved: Enhanced cross-database compatibility for schema introspection
- Resolved: GitHub Issue #1
v1.1.0 (2025-09-28) - Async Bug Fix
- Fixed: Resolved
str can't be used in 'await' expressionerror in MCP server - Improved: NLP query processing now works correctly with Claude Desktop integration
- Enhanced: Added comprehensive test database setup scripts
- Updated: Docker image rebuilt with bug fixes and updated dependencies
v1.0.0 (2025-09-25) - Initial Release
- Initial: Full MCP Database Server implementation
- Added: RESTful API with FastAPI
- Added: Natural language to SQL conversion
- Added: Docker containerization and deployment
- Added: Multi-database support (PostgreSQL, MySQL, SQLite)
Acknowledgments
- FastAPI for the excellent web framework
- HuggingFace Transformers for NL to SQL capabilities
- SQLAlchemy for database abstraction
- The Model Context Protocol (MCP) community
Support
⭐ If this project helped you, please consider giving it a star!