README Documentation
DuneLink
A modern bridge connecting Dune Analytics data to intelligent agents through Model Control Protocol (MCP).
Overview
DuneLink enables seamless integration of blockchain data analytics into your AI applications. By leveraging Dune Analytics' powerful query capabilities with the Model Control Protocol, this service allows LLMs and other AI systems to access on-chain data through simple, natural language interactions.
Core Capabilities
Data Retrieval Tools
| Tool | Description | Use Case |
|---|---|---|
get_latest_result | Retrieves pre-computed query results | Quick access to existing data |
run_query | Executes a query on-demand | Real-time data analysis |
Data Format
All data is returned in CSV format, providing:
- Universal compatibility
- Easy parsing by most data analysis tools
- Human-readable output
Getting Started
System Requirements
- Python 3.10 or higher
- Valid Dune Analytics API key (Get yours here)
Quick Setup
-
Clone & Navigate
git clone https://github.com/olaxbt/dune-query-mcp.git cd dunelink -
Environment Setup
# Create virtual environment python -m venv .venv # Activate it source .venv/bin/activate # Linux/Mac # or .venv\Scripts\activate # Windows # Install dependencies pip install -r requirements.txt -
Configure API Access
# Copy example config cp .env.example .env # Edit with your API key echo "DUNE_API_KEY=your_key_here" > .env
Usage
Running the Service
DuneLink offers two ways to run:
As MCP Service
python run.py
This starts the MCP service on default port 8000.
As Web Server
python flask_app.py
This provides access to the web interface and REST API endpoints.
Integrating with Applications
MCP Client Integration
from mcp.client import Client
# Connect to DuneLink
client = Client("http://localhost:8000")
# Get latest results for a query
csv_data = client.call("get_latest_result", query_id=1234567)
# Execute a query
query_results = client.call("run_query", query_id=1234567)
REST API
| Endpoint | Method | Description |
|---|---|---|
/dune/health | GET | Service health check |
/dune/query/{query_id}/latest | GET | Retrieve latest results |
/dune/query/{query_id}/execute | POST | Run a query |
Example REST Call:
curl -X GET http://localhost:5000/dune/query/1234567/latest
Architecture
dunelink/
├── app/ # Application core
│ ├── __init__.py # Flask & MCP setup
│ ├── routes/ # API endpoint definitions
│ │ └── dune_routes/ # Dune Analytics routes
│ │ └── templates/ # Web interface
│ └── templates/ # Web interface
├── config/ # Configuration files
├── logs/ # Runtime logs
├── flask_app.py # Web server entry point
├── run.py # MCP server entry point
└── requirements.txt # Dependencies
Advanced Configuration
Environment Variables
| Variable | Purpose | Default |
|---|---|---|
| DUNE_API_KEY | Authentication for Dune API | None (Required) |
| PORT | Server port | 8000 |
Performance Tuning
For high-volume query execution:
# Set a higher timeout for long-running queries
export DUNE_QUERY_TIMEOUT=600 # 10 minutes in seconds
Troubleshooting
Common issues and solutions:
| Problem | Solution |
|---|---|
| API Key errors | Ensure .env file exists with valid key |
| Timeout errors | Increase timeout for complex queries |
| CSV parsing issues | Check query returns proper tabular data |
Contributing
Contributions are welcome! Please follow these steps:
- Fork the repository
- Create a feature branch:
git checkout -b feature/amazing-feature - Commit your changes:
git commit -am 'Add some amazing feature' - Push to the branch:
git push origin feature/amazing-feature - Open a Pull Request
License
This project is released under the MIT License. See LICENSE file for details.
Acknowledgments
- Built with FastMCP
- Query functionality powered by Dune Analytics