Allora MCP Server

🚀 Allora MCP Server

This is an implementation of the Model Context Protocol (MCP) server for the Allora Network. It is used to obtain machine learning inference data from the Allora Network and provides access to Allora's prediction market data. Through the standardized Model Context Protocol (MCP), AI systems and applications can seamlessly integrate Allora's prediction market data.

🚀 Quick Start

The Allora MCP server allows AI systems and applications to access Allora's prediction market data through the Model Context Protocol (MCP), providing direct access to Allora's topics, market predictions, and inference data.

✨ Features

Prerequisites

• Node.js 18+ or Docker
• Allora API key (register at developer.allora.network)

Installation

• Docker:

docker run -p 3001:3001 -e PORT=3001 -e ALLORA_API_KEY=your_api_key alloranetwork/mcp-server

# Or use an environment variable file:
docker run -p 3001:3001 --env-file .env alloranetwork/mcp-server

• docker-compose:

docker-compose up

• npx:

npx @alloralabs/mcp-server

• Node.js:

npm run start

💻 Usage Examples

Basic Usage

After the server is running, you can interact with it using any MCP client. The server exposes the following endpoints:

• GET /sse - Server-Sent Events (SSE) connection endpoint for MCP communication
• POST /messages - Message endpoint for MCP communication

Point your LLM/tool to http://localhost:3001/sse to start using the server.

Available Tools

Example Usage (with Claude)

When connecting with Claude or other MCP-compatible AI systems, you can access Allora data:

What topics are available on Allora?

Or get specific prediction data:

What is the current prediction for the Bitcoin price in 8 hours?

📚 Documentation

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

1. Fork the repository
2. Create a feature branch (git checkout -b feature/amazing-feature)
3. Commit your changes (git commit -m 'Add some amazing feature')
4. Push to the branch (git push origin feature/amazing-feature)
5. Open a Pull Request

📄 License

This project is licensed under the MIT License. See the LICENSE file for details.