by GoPlausible
algorand-mcp is an implementation for interacting with the Algorand blockchain. It provides a standardized way for applications to offer context to Large Language Models (LLMs), enabling them to be more effective and useful by providing them with tools, resources, and instructions.
Algorand Model Context Protocol (MCP) is an implementation for interacting with the Algorand blockchain. It provides a standardized way for applications to offer context to Large Language Models (LLMs), enabling them to be more effective and useful by providing them with tools, resources, and instructions. This project includes both a server-side package for blockchain interactions and a client-side package for wallet management and transaction signing.
To use Algorand MCP, you need Node.js v23.6.1 or later and npm v10.2.4 or later.
git clone https://github.com/GoPlausible/algorand-mcp.git
cd algorand-mcp
npm install
npm run build
.env
file to set your configurations.Server Package:
data
and optional metadata
for paginated responses. Errors are also standardized.Client Package (Work in Progress):
Q: What is the Model Context Protocol (MCP)? A: MCP is an open protocol that standardizes how applications provide context to LLMs, enabling them to be more useful and effective by giving them tools, resources, and instructions.
Q: What are the main components of Algorand MCP? A: It consists of a server package for blockchain interactions and a client package for wallet management and transaction signing.
Q: What are the system requirements for Algorand MCP? A: Node.js v23.6.1 or later and npm v10.2.4 or later.
Q: Does the client package support both browser and Node.js environments? A: Yes, the client package is designed for universal compatibility.
Q: How many tools and resources does Algorand MCP provide? A: It provides 125 tools and resources for blockchain interaction, including various API tools for Algod, Indexer, NFDomains, Vestige, Tinyman, and Ultrade, as well as account, application, asset, transaction, and key management tools.
Model context protocol or MCP, is an open protocol that standardizes how applications provide context to LLMs. MCP provides specification standards to give LLMs tools, resources and instructions to be more useful and effective.
MCP Github contains more information and different tools and specifications plus documentation of MCP.
This repository is a Model Context Protocol (MCP) implementation for Algorand blockchain interactions. The implementation consists of:
📦 Packages in this repository:
📦 NPM:
To install or update the Algorand MCP implementation, clone the repository, install the dependencies and build the project":
First check node version to be 23.6.1 or later:
node -v
Upgrade to 23.6.1 or later if needed!
Then check the Claude or Cursor container folders to have mcp-servers folder (if not create one):
mkdir PATH_ON_YOUR_MACHINE/Claude/mcp-servers
# or for Cursor
mkdir PATH_ON_YOUR_MACHINE/Cursor/mcp-servers
Then clone this repository under mcp-servers folder and install dependencies:
cd PATH_ON_YOUR_MACHINE/Claude/mcp-servers
# or for Cursor
cd PATH_ON_YOUR_MACHINE/Cursor/mcp-servers
# Clone the repository
git clone https://github.com/GoPlausible/algorand-mcp.git
cd algorand-mcp
# Install dependencies
npm install
# Build the project
npm run build
# Edit the .env file to set your configurations
And you are done! Now you can open you MCP config and add the server as :
{
"mcpServers": {
"algorand-mcp": {
"command": "node",
"args": [
"PATH_ON_YOUR_MACHINE/Claude/mcp-servers/algorand-mcp/packages/server/dist/index.js"
],
"env": {
"ALGORAND_NETWORK": "testnet",
"ALGORAND_ALGOD_API": "https://testnet-api.algonode.cloud/v2",
"ALGORAND_ALGOD": "https://testnet-api.algonode.cloud",
"ALGORAND_INDEXER_API": "https://testnet-idx.algonode.cloud/v2",
"ALGORAND_INDEXER": "https://testnet-idx.algonode.cloud",
"ALGORAND_ALGOD_PORT": "",
"ALGORAND_INDEXER_PORT": "",
"ALGORAND_TOKEN": "",
"ALGORAND_AGENT_WALLET": "problem aim online jaguar upper oil flight stumble mystery aerobic toy avoid file tomato moment exclude witness guard lab opera crunch noodle dune abandon broccoli",
"NFD_API_URL": "https://api.nf.domains",
"NFD_API_KEY": "",
"TINYMAN_ACTIVE": "false",
"ULTRADE_ACTIVE": "false",
"ULTRADE_API_URL": "https://api.ultrade.io",
"VESTIGE_ACTIVE": "false",
"VESTIGE_API_URL": "https://api.vestigelabs.org",
"VESTIGE_API_KEY": "",
"ITEMS_PER_PAGE": "10"
}
}
}
}
Make sure yopu change the paths to match your local system's paths.
For example on MACOS and Claud, the path would be something like this:
{
"mcpServers": {
"algorand-mcp": {
"command": "node",
"args": [
" /Users/YOUR_USERNAME/Library/Application\ Support/Claude/mcp-servers/algorand-mcp/packages/server/dist/index.js"
]
}
}
}
The project follows a modular architecture with two main packages:
Server Package (@algorand-mcp/server
)
Client Package (@algorand-mcp/client
)
algorand-mcp/
├── packages/
│ ├── client/ # Client Package
│ │ ├── src/
│ │ │ ├── index.ts # Client entry point and wallet management
│ │ │ └── LocalWallet.ts # Local wallet implementation
│ │ ├── package.json
│ │ └── tsconfig.json
│ └── server/ # Server Package
│ ├── src/
│ │ ├── resources/ # MCP Resources (User-invokable endpoints)
│ │ │ ├── knowledge/ # Documentation and taxonomy
│ │ │ │ ├── taxonomy/ # Markdown documentation
│ │ │ │ └── index.ts # Knowledge resource handler
│ │ │ ├── wallet/ # Wallet management
│ │ │ │ └── index.ts # Wallet resource handler
│ │ │ └── index.ts # Resource registration
│ │ ├── tools/ # MCP Tools (Agent-invokable operations)
│ │ │ ├── accountManager.ts # Account operations
│ │ │ ├── algodManager.ts # Node interactions
│ │ │ ├── utilityManager.ts # Utility functions
│ │ │ ├── apiManager/ # API Tools
│ │ │ │ ├── algod/ # Algod API tools
│ │ │ │ ├── indexer/ # Indexer API tools
│ │ │ │ ├── nfd/ # NFDomains tools
│ │ │ │ ├── vestige/ # Vestige DeFi tools
│ │ │ │ ├── tinyman/ # Tinyman AMM tools
│ │ │ │ └── ultrade/ # Ultrade DEX tools
│ │ │ └── transactionManager/ # Transaction handling
│ │ ├── env.ts # Environment configuration
│ │ └── index.ts # Server entry point
│ ├── package.json
│ └── tsconfig.json
├── package.json # Root package file
└── tsconfig.json # Root TypeScript config
All responses follow a standardized format:
{
"data": {
// Response data here
},
"metadata": { // Only for paginated responses
"totalItems": number,
"itemsPerPage": number,
"currentPage": number,
"totalPages": number,
"hasNextPage": boolean,
"pageToken": string,
"arrayField": string // Name of paginated array field
}
}
Errors are returned in a standardized format:
{
"error": {
"code": string,
"message": string
}
}
The Algorand MCP implementation provides 125 tools and resources for blockchain interaction:
MIT
Please log in to share your review and rating for this MCP.
Discover more MCP servers with similar functionality and use cases
by zed-industries
Provides real-time collaborative editing powered by Rust, enabling developers to edit code instantly across machines with a responsive, GPU-accelerated UI.
by cline
Provides autonomous coding assistance directly in the IDE, enabling file creation, editing, terminal command execution, browser interactions, and tool extension with user approval at each step.
by continuedev
Provides continuous AI assistance across IDEs, terminals, and CI pipelines, offering agents, chat, inline editing, and autocomplete to accelerate software development.
by github
Enables AI agents, assistants, and chatbots to interact with GitHub via natural‑language commands, providing read‑write access to repositories, issues, pull requests, workflows, security data and team activity.
by block
Automates engineering tasks by installing, executing, editing, and testing code using any large language model, providing end‑to‑end project building, debugging, workflow orchestration, and external API interaction.
by RooCodeInc
An autonomous coding agent that lives inside VS Code, capable of generating, refactoring, debugging code, managing files, running terminal commands, controlling a browser, and adapting its behavior through custom modes and instructions.
by lastmile-ai
A lightweight, composable framework for building AI agents using Model Context Protocol and simple workflow patterns.
by firebase
Provides a command‑line interface to manage, test, and deploy Firebase projects, covering hosting, databases, authentication, cloud functions, extensions, and CI/CD workflows.
by gptme
Empowers large language models to act as personal AI assistants directly inside the terminal, providing capabilities such as code execution, file manipulation, web browsing, vision, and interactive tool usage.