🤖 MCP Dataset Onboarding Server

A FastAPI-based MCP (Model-Compatible Protocol) server for automating dataset onboarding using Google Drive as both input source and mock catalog.

🔒 SECURITY FIRST - READ THIS BEFORE SETUP

⚠️ This repository contains template files only. You MUST configure your own credentials before use.

📖 Read

🚨 Never commit service account keys or real folder IDs to version control!

Features

Automated Dataset Processing: Complete workflow from raw CSV/Excel files to cataloged datasets
Google Drive Integration: Uses Google Drive folders as input source and catalog storage
Metadata Extraction: Automatically extracts column information, data types, and basic statistics
Data Quality Rules: Suggests DQ rules based on data characteristics
Contract Generation: Creates Excel contracts with schema and DQ information
Mock Catalog: Publishes processed artifacts to a catalog folder
🤖 Automated Processing: Watches folders and processes files automatically
🌐 Multiple Interfaces: FastAPI server, MCP server, CLI tools, and dashboards

Project Structure

├── main.py # FastAPI server and endpoints ├── mcp_server.py # True MCP protocol server for LLM integration ├── utils.py # Google Drive helpers and DQ functions ├── dataset_processor.py # Centralized dataset processing logic ├── auto_processor.py # 🤖 Automated file monitoring ├── start_auto_processor.py # 🚀 Easy startup for auto-processor ├── processor_dashboard.py # 📊 Monitoring dashboard ├── dataset_manager.py # CLI tool for managing datasets ├── local_test.py # Local processing script ├── auto_config.py # ⚙️ Configuration management ├── requirements.txt # Python dependencies ├── Dockerfile # Container configuration ├── .env.template # Environment variables template ├── .gitignore # Security: excludes sensitive files ├── SECURITY_SETUP.md # 🔒 Security configuration guide ├── processed_datasets/ # Organized output folder │ └── [dataset_name]/ # Individual dataset folders │ ├── [dataset].csv # Original dataset │ ├── [dataset]_metadata.json │ ├── [dataset]_contract.xlsx │ ├── [dataset]_dq_report.json │ └── README.md # Dataset summary └── README.md # This file

🚀 Quick Start

1. Security Setup (REQUIRED)

# 1. Read the security guide cat SECURITY_SETUP.md # 2. Set up your Google service account (outside this repo) # 3. Configure your environment variables cp .env.template .env # Edit .env with your actual values # 4. Verify no sensitive files will be committed git status

2. Installation

# Install dependencies pip install -r requirements.txt # Test the setup python local_test.py

3. Choose Your Interface

🤖 Fully Automated (Recommended)

# Start auto-processor - upload files and walk away! python start_auto_processor.py

🌐 API Server

# Start FastAPI server python main.py

🧠 LLM Integration (MCP)

# Start MCP server for Claude Desktop, etc. python mcp_server.py

🖥️ Command Line

# Manual dataset management python dataset_manager.py list python dataset_manager.py process YOUR_FILE_ID

🎯 Usage Scenarios

Scenario 1: Set-and-Forget Automation

python start_auto_processor.py
Upload files to Google Drive
Files processed automatically within 30 seconds
Monitor with python processor_dashboard.py --live

Scenario 2: LLM-Powered Data Analysis

Configure MCP server in Claude Desktop
Chat: "Analyze the dataset I just uploaded"
Claude uses MCP tools to process and explain your data

Scenario 3: API Integration

python main.py
Integrate with your data pipelines via REST API
Programmatic dataset onboarding

📊 What You Get

For each processed dataset:

📄 Original File: Preserved in organized folder
📋 Metadata JSON: Column info, types, statistics
📊 Excel Contract: Professional multi-sheet contract
🔍 Quality Report: Data quality assessment
📖 README: Human-readable summary

🛠️ Available Tools

FastAPI Endpoints

/tool/extract_metadata - Analyze dataset structure
/tool/apply_dq_rules - Generate quality rules
/process_dataset - Complete workflow
/health - System health check

MCP Tools (for LLMs)

extract_dataset_metadata - Dataset analysis
generate_data_quality_rules - Quality assessment
process_complete_dataset - Full pipeline
list_catalog_files - Catalog browsing

CLI Commands

dataset_manager.py list - Show processed datasets
auto_processor.py --once - Single check cycle
processor_dashboard.py --live - Real-time monitoring

🔧 Configuration

Environment Variables (.env)

GOOGLE_SERVICE_ACCOUNT_KEY_PATH=path/to/your/key.json MCP_SERVER_FOLDER_ID=your_input_folder_id MCP_CLIENT_FOLDER_ID=your_output_folder_id

Auto-Processor Settings (auto_config.py)

Check interval: 30 seconds
Supported formats: CSV, Excel
File age threshold: 1 minute
Max files per cycle: 5

📈 Monitoring & Analytics

# Current status python processor_dashboard.py # Live monitoring (auto-refresh) python processor_dashboard.py --live # Detailed statistics python processor_dashboard.py --stats # Processing history python auto_processor.py --list

🐳 Docker Deployment

# Build docker build -t mcp-dataset-server . # Run (mount your service account key securely) docker run -p 8000:8000 \ -v /secure/path/to/key.json:/app/keys/key.json \ -e GOOGLE_SERVICE_ACCOUNT_KEY_PATH=/app/keys/key.json \ -e MCP_SERVER_FOLDER_ID=your_folder_id \ mcp-dataset-server

🔍 Troubleshooting

Common Issues

No files detected: Check Google Drive permissions
Processing errors: Verify service account access
MCP not working: Check Claude Desktop configuration

Debug Commands

# Test Google Drive connection python -c "from utils import get_drive_service; print('✅ Connected')" # Check auto-processor status python auto_processor.py --once # Verify MCP server python test_mcp_server.py

🤝 Contributing

Fork the repository
Create a feature branch
Never commit sensitive data
Test your changes
Submit a pull request

📚 Documentation

SECURITY_SETUP.md - Security configuration
AUTOMATION_GUIDE.md - Automation features
MCP_INTEGRATION_GUIDE.md - LLM integration

📄 License

MIT License

🎉 What Makes This Special

🔒 Security First: Proper credential management
🤖 True Automation: Zero manual intervention
🧠 LLM Integration: Natural language data processing
📊 Professional Output: Enterprise-ready documentation
🔧 Multiple Interfaces: API, CLI, MCP, Dashboard
📈 Real-time Monitoring: Live processing status
🗂️ Perfect Organization: Structured output folders

Transform your messy data files into professional, documented, quality-checked datasets automatically! 🚀

This server cannot be installed

security - not tested

license - permissive license

quality - not tested

How are these scores calculated?

Related Resources

GitHub Repository

Need Help?

Report Issue

Related MCP Servers

mcp-server-data-exploration
reading-plus-ai
A
security
-
license
A
quality
Enables autonomous data exploration on .csv-based datasets, providing intelligent insights with minimal effort.
Last updated -
2
487
MIT License
Google Drive MCP Server
felores
-
security
A
license
-
quality
Enables integration with Google Drive for listing, reading, and searching over files, supporting various file types with automatic export for Google Workspace files.
Last updated -
621
58
MIT License
Google Drive MCP Server
isaacphi
-
security
-
license
-
quality
Integrates with Google Drive to enable listing, searching, and reading files, plus reading and writing to Google Sheets.
Last updated -
202
210
MIT License
Smartsheet MCP Server
terilios
A
security
A
license
A
quality
Provides seamless integration with Smartsheet, enabling automated operations on Smartsheet documents through a standardized interface that bridges AI-powered automation tools with Smartsheet's collaboration platform.
Last updated -
11
MIT License

View all related MCP servers

Appeared in Searches

Help with creating and importing data into spreadsheets/tables