Avalanche MCP server

Provides a bridge to the Avalanche blockchain CLI, enabling developers to interact with blockchain configurations, network management, and VM publishing across Mainnet, Fuji Testnet, and local development environments.
Back to servers
Provider
Utku Ceyhun Yilmaz
Release date
Mar 17, 2025
Language
TypeScript
Stats
1 star

The Avalanche MCP Tools provide a standardized interface that allows AI assistants to interact directly with the Avalanche blockchain through natural language commands. This implementation enables users to query blockchain data, manage assets, and execute complex operations without needing to remember technical commands or syntax.

Getting Started

Prerequisites

Before installing Avalanche MCP Tools, ensure you have:

  • Node.js 16 or higher
  • Avalanche CLI installed and in your PATH
  • Access to an Avalanche node (local or remote)

Installation

To install the Avalanche MCP Tools:

# Clone the repository
git clone https://github.com/yourusername/avalanche-mcp-tools.git
cd avalanche-mcp-tools

# Install dependencies
npm install

# Build the project
npm run build

Running the MCP Server

Start the MCP server with:

npm start

The server runs on stdio, making it compatible with AI assistants that support the Model Context Protocol (MCP).

Available Tools

Blockchain Management

Currently implemented tools:

  • blockchainList - Retrieves a list of all created Avalanche Blockchain configurations
  • blockchainPublish - Publishes a Blockchain's Virtual Machine to a repository

Coming Soon

Additional functionality being developed:

  • Subnet Management - Creation, deployment, and monitoring of subnets
  • Key Management - Generate keys, manage addresses, and handle signing operations
  • Transaction Operations - Build, sign, and submit transactions with monitoring capabilities

Using with AI Assistants

Avalanche MCP Tools can be integrated with Claude or other AI assistants that support MCP tools. Below is an example conversation:

User: "List all my avalanche blockchains"

Claude: "I'll check your Avalanche blockchains. [Uses blockchainList MCP tool] Here are your Avalanche blockchains:

  • mySubnet (deployed)
  • testChain
  • devNet"

Use Cases

For Regular Users

  • Chat naturally with Avalanche through your preferred AI interface
  • Manage accounts and send payments through conversational interactions
  • Explore blockchain assets without learning technical commands

For Developers

  • Add Avalanche capabilities to applications without Avalanche-specific code
  • Integrate MCP tools into AI agents for autonomous blockchain operations
  • Access Avalanche functionality directly from within your code editor
  • Speed up development from prototyping through production

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.

Want to 10x your AI skills?

Get a free account and learn to code + market your apps using AI (with or without vibes!).

Nah, maybe later