DEV Community: Shabiha

Building a Local AI-Powered Receipt Sorter with Tiger Cloud and MCP for Freelancers

Shabiha — Tue, 13 Oct 2026 15:30:21 +0000

During this Global Hack Week and Hacktoberfest challenge, I wanted to build something practical that solves a real-world problem for small business owners and freelancers. Receipts, invoices, and expense tracking are often tedious tasks, and relying on heavy cloud-based AI APIs can risk sensitive client data while incurring recurring costs.

To solve this, I built Local AI Receipt Sorter—a local-first tool powered by open-source AI logic, secure database partitioning, and Model Context Protocol (MCP) integration with Tiger Cloud.

1. Project Folder Structure

To keep the application modular, clean, and easy to maintain, the project follows a standard production-ready folder layout:

local-ai-receipt/
│
├── .env.example            # Environment variables template (Database URLs, API keys)
├── .gitignore              # Files and folders to ignore in Git
├── README.md               # Comprehensive project documentation
├── requirements.txt        # Python dependencies (psycopg2, requests, etc.)
│
├── config/
│   └── mcp_config.json     # Tiger MCP configuration for AI assistant integration
│
├── src/
│   ├── __init__.py         # Package initializer
│   ├── database.py         # Tiger Cloud / TimescaleDB connection and hypertable setup
│   ├── parser.py           # Local text parsing and receipt data extraction logic
│   └── main.py             # Main entry point running the receipt sorting pipeline
│
└── data/
    └── sample_receipts.txt # Sample raw text data used for testing and processing

2. System Architecture & Data Flow

Here is how the components interact locally and communicate with the Tiger Cloud database via MCP:

[ Raw Receipt / Invoice Text ]
               │
               ▼
  ┌─────────────────────────┐
  │   src/parser.py         │  <--- Local Regex / Open-Weight Parsing
  └────────────┬────────────┘
               │
               ▼
  ┌─────────────────────────┐
  │   src/database.py       │  <--- Tiger Cloud (TimescaleDB Hypertable)
  └────────────┬────────────┘
               │
               ▼
  ┌─────────────────────────┐
  │   Tiger MCP & Agent     │  <--- Natural Language Queries via AI Assistant

3. Step-by-Step Technical Implementation

Step 1: Database Hypertable Setup (src/database.py)

In Tiger Cloud, time-series financial logs are structured into hypertables for efficient indexing and scaling. The database script initializes the table schema:

`CREATE TABLE IF NOT EXISTS receipts (
id SERIAL,
vendor_name TEXT,
category TEXT,
total_amount NUMERIC,
created_at TIMESTAMPTZ NOT NULL
);

-- Converting to a TimescaleDB hypertable for optimized time-series storage
SELECT create_hypertable('receipts', 'created_at', if_not_exists => TRUE);`

Step 2: CLI & MCP Integration

To link local development tools with Tiger Cloud securely and manage records via conversational prompts:

tiger auth login
tiger mcp install

This automatically wires the Model Context Protocol (MCP) configuration into your AI development environment (config/mcp_config.json), allowing instant natural language querying of stored receipts.

4. Why Open Innovation Won Here

Zero Data Leakage: Financial information remains fully partitioned and secure under local and trusted database environments without exposing raw client data to third-party model servers.
Cost Efficiency: By avoiding expensive third-party hosted API inference calls for basic structuring, the solution costs virtually nothing to run.
Scalability: Tiger Cloud's time-series hypertable architecture ensures lightning-fast queries even as thousands of monthly receipts accumulate.

Conclusion & Next Steps

Building this side-hustle utility proved how powerful open-weight models, local toolings, and Tiger Cloud MCP can be when combined. I have already tested it with a local freelancer friend who found it immensely helpful for tax season preparation!

Check out the repository on GitHub: SithubShabihaz/local-ai-receipt

Happy coding, and let's keep building open! #mlhacks #devchallenge #hf26challenge #tigerdata

Building Smart Cloud Workflows: My Experience Integrating Tiger Cloud and MCP with Google Antigravity

Shabiha — Mon, 12 Oct 2026 10:45:57 +0000

During this Global Hack Week, I embarked on a journey to explore advanced cloud infrastructure, repository management best practices, and AI-driven workflow integrations. One of the most exciting parts of this learning curve was connecting Tiger Cloud with my AI agent using the Tiger CLI and Model Context Protocol (MCP).

Here is a breakdown of what I built, how it works, and the technical hurdles I overcame along the way.

1. Establishing Repository Best Practices

Before diving into cloud automation, I focused on foundational software engineering standards for project repositories (such as the Mergington High School extracurricular project). To ensure clean collaboration and security, I implemented:

CONTRIBUTING.md to guide future contributors on contribution workflows.
CODEOWNERS to automate review assignments.
SECURITY.md to define vulnerability reporting policies.
Custom pull request templates to keep feature submissions standardized.

2. Setting Up Tiger Cloud and MCP Integration

Moving into cloud infrastructure, the goal was to give my AI assistant direct, natural language access to cloud resources via the Model Context Protocol (MCP).

Step-by-Step Implementation:

1._ Authentication:_ Authenticated the local environment securely using the Tiger CLI:

tiger auth login

And configured write protections for production services to safeguard critical environments.

2. Installing the MCP Server:
Ran the interactive installation command to wire the Tiger MCP binary directly into my development environment:

tiger mcp install

This automatically generated the required configuration file at C:\Users\Admin.gemini\antigravity\mcp_config_json for Google Antigravity.

3. Interacting via Natural Language:
Once configured and restarted, the AI assistant gained the capability to manage cloud resources seamlessly. Instead of manual CLI navigation, I could prompt commands like:

- "List my Tiger Cloud services"
- "Help me create a new database schema for my application"

Key Takeaways

Integrating Tiger MCP into an AI agent environment bridges the gap between conversational AI and heavy backend infrastructure management. It drastically reduces context-switching and allows developers to query data, inspect tables, and manage deployments using plain language.

Happy coding, and see you at the next hackathon! #mlhacks

🌟 Learning, Building & Dreaming Big! 🚀

Shabiha — Sun, 11 Oct 2026 08:21:07 +0000

Hey, developers! 👋💻

I'm thrilled to be part of MLH Global Hack Week! 🎉 As a Class 8 student passionate about coding, AI, and technology, I'm excited to challenge myself, explore new ideas, and turn my creativity into real projects.

My journey as a developer is just beginning, and I'm ready to learn something new, step outside my comfort zone, and grow one challenge at a time. 💡

Big dreams start with small steps. Let's build something amazing together! 🌍✨

MLH #GlobalHackWeek #DevChallenge #CodingJourney #ArtificialIntelligence #FutureDeveloper #KeepLearning