Monad MCP Tutorial
This project demonstrates how to create a MCP server that interacts with the Monad testnet. The MCP server provides a tool for checking MON token balances on the Monad testnet.
What is MCP?
The Model Context Protocol (MCP) is a standard that allows AI models to interact with external tools and services.
In this tutorial, we're creating an MCP server that allows MCP Client (Claude Desktop) to query Monad testnet to check MON balance of an account.
Prerequisites
- Node.js (v16 or later)
npmoryarn- Claude Desktop
Getting Started
- Clone this repository
git clone https://github.com/monad-developers/monad-mcp-tutorial.git
- Install dependencies:
npm install
Building the MCP server
Monad Testnet related configuration is already added to index.ts in the src folder.
Define the server instance
// Create a new MCP server instance
const server = new McpServer({
name: "monad-testnet",
version: "0.0.1",
// Array of supported tool names that clients can call
capabilities: ["get-mon-balance"]
});
Defining the MON balance tool
Below is the scaffold of the get-mon-balance tool:
server.tool(
// Tool ID
"get-mon-balance",
// Description of what the tool does
"Get MON balance for an address on Monad testnet",
// Input schema
{
address: z.string().describe("Monad testnet address to check balance for"),
},
// Tool implementation
async ({ address }) => {
// code to check MON balance
}
);
Let's add the MON balance check implementation to the tool:
server.tool(
// Tool ID
"get-mon-balance",
// Description of what the tool does
"Get MON balance for an address on Monad testnet",
// Input schema
{
address: z.string().describe("Monad testnet address to check balance for"),
},
// Tool implementation
async ({ address }) => {
try {
// Check MON balance for the input address
const balance = await publicClient.getBalance({
address: address as `0x${string}`,
});
// Return a human friendly message indicating the balance.
return {
content: [
{
type: "text",
text: `Balance for ${address}: ${formatUnits(balance, 18)} MON`,
},
],
};
} catch (error) {
// If the balance check process fails, return a graceful message back to the MCP client indicating a failure.
return {
content: [
{
type: "text",
text: `Failed to retrieve balance for address: ${address}. Error: ${
error instanceof Error ? error.message : String(error)
}`,
},
],
};
}
}
);
Initialize the transport and server from the main function
async function main() {
// Create a transport layer using standard input/output
const transport = new StdioServerTransport();
// Connect the server to the transport
await server.connect(transport);
console.error("Monad testnet MCP Server running on stdio");
}
Build the project
npm run build
The server is now ready to use!
Adding the MCP server to Claude Desktop
- Open "Claude Desktop"

- Open Settings
Claude > Settings > Developer

- Open
claude_desktop_config.json

- Add details about the MCP server and save the file.
{
"mcpServers": {
...
"monad-mcp": {
"command": "node",
"args": [
"/<path-to-project>/build/index.js"
]
}
}
}
- Restart "Claude Desktop"
Using the MCP server
Here's the final result

Further Resources
mcp-monad
mcp-monad
mcp-monad
Recommend MCP Servers 💡
@token-metrics-ai/mcp
The Token Metrics Model Context Protocol (MCP) server provides comprehensive cryptocurrency data, analytics, and insights, enabling AI assistants to access real-time crypto market data, trading signals, price predictions, and advanced analytics.
ramp-mcp
A Model Context Protocol server for Ramp, integrating with their Developer API to fetch, process, and analyze financial data using an ephemeral SQLite database.
crypto-sentiment-mcp
An MCP server that delivers cryptocurrency sentiment analysis to AI agents.
algorand-mcp
Algorand Model Context Protocol (MCP) implementation for blockchain interactions, providing LLMs with tools and resources to manage accounts, assets, and transactions on the Algorand network, including integrations with DeFi and NFT services.

@coingecko/coingecko-mcp
The official CoinGecko MCP Server provides real-time and historical cryptocurrency price and market data, enabling AI models and agents to securely interact with CoinGecko's extensive financial data via various transport methods.
metatrader-mcp-server
Model Context Protocol (MCP) to enable AI LLMs to trade using MetaTrader platform