About π Sustainable Spending Dashboard
Sustainable Spending Dashboard is a Streamlit app that analyzes Bunq spending and estimates its carbon impact. It combines categorized expenses, sustainability indicators, offset transfers, and a leaderboard for climate-conscious financial tracking.
Key features
- 01Spending categorization
- 02COβ estimates per spend
- 03Green, Yellow, Red zones
- 04Dashboard charts and insights
- 05Bunq offset transfers
- 06Sustainability leaderboard
Use cases
- 01Review spending categories and trends
- 02Compare COβ impact across spending
- 03Transfer funds to offset emissions
- 04Compare offset-to-spend ratios
MCP support
The project includes MCP servers in its source structure and describes the dashboard as using MCP servers for Bunq-related sustainable spending. It does not specify the exposed tools.
Configuration
Local server config is the same for every client. Copy it into your clientβs MCP config file.
We havenβt collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEπ Sustainable Spending Dashboard
An AI-powered dashboard that analyzes your spending habits, estimates your carbon footprint, and encourages climate-friendly financial decisions β built with Streamlit, LLMs, and Bunq.
The Dashboard looks like this(cool right!)

π‘ What It Does
This dashboard connects financial data with climate awareness using the power of LLMs. It helps you:
- Understand where your money goes πΈ
- See how your spending impacts the planet π±
- Take climate action via automated COβ offset transfers β»οΈ
- Compete (gently!) with others in a sustainability leaderboard π
π§ Powered By
| Technology | Role |
|---|---|
Streamlit | Dashboard UI & interactivity |
pydantic_ai | Agent orchestration + LLM I/O |
Gemini / OpenAI | Spending & COβ reasoning |
Bunq SDK | Carbon offset transfers |
Pandas, Matplotlib | Data processing & charts |
π Project Structure
.
βββ src/
| |- dashboard.py # Streamlit dashboard
| |- bunq_agents.py # Pydantic agents & logic
| |- mcp_ # MCP servers
| |- utils/wrapper.py Bunq integration wrapper
βββ data/
β βββ transactions.csv # Sample transactions
βββ requirements.txt
βββ README.md
β¨ Features
β
Classify spending into intuitive categories
β
Calculate total COβ emissions and COβ per β¬ spent
β
Assign a sustainability zone (Green / Yellow / Red)
β
Visualize insights in a modern, intuitive dashboard
β
Transfer offset amounts to a Bunq green account π
β
Display motivational messages like βyou planted 3 trees!β π³
β
See how you compare on a gamified leaderboard π
π Setup Instructions
1. Clone the Repo
git clone https://github.com/your-username/bunq-hackathon-agents-6.0.git
cd bunq-hackathon-agents-6.0
- Create a Virtual Environment
python -m venv venv
source venv/bin/activate # On Windows: venv\Scripts\activate
- Install Requirements
pip install -r requirements.txt
- Add a .env File Create a .env file in the root folder with:
BUNQ_API_KEY=your_bunq_api_key_here
- π Run the App
streamlit run dashboard.py
π Example Insights
πΏ You just offset 25 kg of COβ β thatβs like planting 1.2 trees! π¬ Most of your spending goes to groceries and travel. Try biking more often to reduce your footprint. π¦ You transferred β¬40 to your green account. Nice work!
π Leaderboard Logic
Users are ranked by their Offset Amount / Spend Ratio. The current user is highlighted in light orange for visibility:
The higher the ratio, the better you're doing for the planet π
β Sustainability Zone Logic
π’ Green: COβ per β¬ < 0.4 β Excellent!
π Yellow: 0.4 β€ COβ per β¬ β€ 0.6 β Room to improve
π΄ Red: COβ per β¬ > 0.6 β Consider more eco-friendly habits
Your zone is displayed as a dynamic badge in the app.
Created with π during the Bunq Hackathon.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.