allora
MCP server with tools based on the Allora SDK for interacting with the Allora Network.
claude mcp add --transport stdio allora-network-allora-mcp-server docker run -p 3001:3001 -e PORT=3001 -e ALLORA_API_KEY=your_api_key alloranetwork/mcp-server \ --env PORT="Port the MCP server should listen on (default 3001)" \ --env ALLORA_API_KEY="Allora API key for accessing Allora data"
How to use
The Allora MCP Server exposes a standardized interface for querying Allora prediction markets data via the Model Context Protocol (MCP). Once the server is running, clients can subscribe to real-time updates and request specific inferences and topics through the MCP endpoints. The server exposes two primary endpoints: GET /sse for establishing an SSE-based MCP communication stream and POST /messages for sending MCP messages to interact with the data. Point your MCP client or LLM tooling to http://localhost:3001/sse to start receiving data.
Available Tools include: list_all_topics to fetch all Allora topics, and get_inference_by_topic_id to retrieve inference data for a given topic ID. These tools enable you to discover available markets and fetch current predictions or inference data for any topic. You can integrate these tools into your prompts or automated workflows to retrieve up-to-date Allora market information and feed it into your AI systems or decision workflows.
How to install
Prerequisites:
- Docker or Node.js 18+ (choose one method below)
- An Allora API key (sign up at https://developer.allora.network)
Option A: Docker (recommended)
- Ensure Docker is installed and running.
- Run the MCP server image (replace with your desired port if needed): docker run -p 3001:3001 -e PORT=3001 -e ALLORA_API_KEY=your_api_key alloranetwork/mcp-server
- The server will be available at http://localhost:3001/sse for MCP clients.
Option B: npx (Node.js-based, if you prefer running directly from npm registry)
- Ensure Node.js 18+ is installed.
- Run: npx @alloralabs/mcp-server
- Follow the console output to determine the listening port (default 3001).
Option C: Node.js (local source code)
- Ensure Node.js 18+ is installed.
- Clone the repository and install dependencies: npm install
- Start the server: npm run start
- Access the MCP endpoints at http://localhost:3001/sse (adjust port if needed).
Prerequisites recap:
- Docker or Node.js 18+ installed
- Allora API key
- Network access to Allora services
Additional notes
- The ALLORA_API_KEY must be kept secret; do not share in public repos.
- If running behind a reverse proxy, ensure proper CORS and SSE support for /sse endpoint.
- The server is designed to listen on port 3001 by default; adjust the PORT environment variable if necessary.
- If you encounter connection errors, verify that the API key is valid and that the Allora service is reachable from your environment.
- You can use either Docker or npx/Node.js to run the MCP server; choose the method that best fits your deployment workflow.
Related MCP Servers
zen
Selfhosted notes app. Single golang binary, notes stored as markdown within SQLite, full-text search, very low resource usage
MCP -Deepseek_R1
A Model Context Protocol (MCP) server implementation connecting Claude Desktop with DeepSeek's language models (R1/V3)
mcp-fhir
A Model Context Protocol implementation for FHIR
mcp
Inkdrop Model Context Protocol Server
mcp-appium-gestures
This is a Model Context Protocol (MCP) server providing resources and tools for Appium mobile gestures using Actions API..
dubco -npm
The (Unofficial) dubco-mcp-server enables AI assistants to manage Dub.co short links via the Model Context Protocol. It provides three MCP tools: create_link for generating new short URLs, update_link for modifying existing links, and delete_link for removing short links.