Allora MCP Server

This is a Model Context Protocol (MCP) server implementation for fetching machine learning inferences from the Allora Network, providing access to Allora's prediction markets data through the Model Context Protocol.

Overview

The Allora MCP server allows AI systems and applications to access Allora prediction markets data through the standardized Model Context Protocol (MCP), enabling seamless integration of prediction market data into AI workflows. This server provides direct access to Allora topics, market predictions, and inference data.

Prerequisites

• Node.js 18 or higher
• An Allora API key (sign up at alloralabs.com)

Setup

1. Clone the repository

git clone https://github.com/your-username/allora-mcp.git
cd allora-mcp

2. Install dependencies

npm install

3. Set up environment variables

Create a .env file in the project root (or copy from .env.example):

PORT=3001
ALLORA_API_KEY=your_api_key

Development

npm run dev

Building

npm run build

Running

npm start

Docker

Building the Docker Image

docker build -t allora-mcp .

Running with Docker

# Run the container
docker run -p 3001:3001 -e PORT=3001 -e ALLORA_API_KEY=your_api_key allora-mcp

# Or with environment variables in a file
docker run -p 3001:3001 --env-file .env allora-mcp

Docker Compose (optional)

Create a docker-compose.yml file:

version: '3'
services:
  allora-mcp:
    build: .
    ports:
      - "3001:3001"
    environment:
      - PORT=3001
      - ALLORA_API_KEY=your_api_key

Then run:

docker-compose up

API Usage

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

• GET /sse - SSE connection endpoint for MCP communications
• POST /messages - Message endpoint for MCP communications

Available Tools

Example Usage with Claude

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

What topics are available in Allora?

Or get specific inference data:

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

Contributing

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

1. Fork the repository
2. Create your 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.