MCP server
by mcpdotdirect
Connect to Starknet for seamless blockchain data queries, token management, and transactions on mainnet and sepolia.
Connects AI agents to Starknet blockchain networks for querying account balances, resolving Starknet IDs, and accessing network information. Works with both mainnet and sepolia testnets.
Starknet is a community-built MCP server published by mcpdotdirect that provides AI assistants with tools and capabilities via the Model Context Protocol. Connect to Starknet for seamless blockchain data queries, token management, and transactions on mainnet and sepolia. It is categorized under developer tools. This server exposes 25 tools that AI clients can invoke during conversations and coding sessions.
You can install Starknet in your AI client of choice. Use the install panel on this page to get one-click setup for Cursor, Claude Desktop, VS Code, and other MCP-compatible clients. This server runs locally on your machine via the stdio transport.
MIT
Starknet is released under the MIT license. This is a permissive open-source license, meaning you can freely use, modify, and distribute the software.
Add new capabilities to Claude beyond text generation
Example
Access external data sources, execute code, interact with tools and services
Transform Claude from chatbot to action-taking agent
Provide Claude with access to relevant context and data
Example
Load project documentation, access knowledge bases, query databases
Get more accurate, context-aware responses
Automate multi-step workflows combining AI and external tools
Example
Research → Summarize → Create document → Send notification
Complete complex tasks end-to-end without manual steps
Share your MCP server with the developer community
Starknet is among the better-indexed MCP projects we tried; the explainx.ai summary tracks the official description.
Starknet is a well-scoped MCP server in the explainx.ai directory — install snippets and categories matched our Claude Code setup.
We evaluated Starknet against two servers with overlapping tools; this profile had the clearer scope statement.
We wired Starknet into a staging workspace; the listing’s GitHub and npm pointers saved time versus hunting across READMEs.
Starknet reduced integration guesswork — categories and install configs on the listing matched the upstream repo.
According to our notes, Starknet benefits from clear Model Context Protocol framing — fewer ambiguous “AI plugin” claims.
I recommend Starknet for teams standardizing on MCP; the explainx.ai page compares cleanly with sibling servers.
Starknet has been reliable for tool-calling workflows; the MCP profile page is a good permalink for internal docs.
We wired Starknet into a staging workspace; the listing’s GitHub and npm pointers saved time versus hunting across READMEs.
We evaluated Starknet against two servers with overlapping tools; this profile had the clearer scope statement.
showing 1-10 of 45
A comprehensive Model Context Protocol (MCP) server for the Starknet blockchain. This server provides AI agents with the ability to interact with Starknet networks, query blockchain data, manage wallets, and interact with smart contracts.
<a href="https://glama.ai/mcp/servers/@mcpdotdirect/starknet-mcp-server"> <img width="380" height="200" src="https://glama.ai/mcp/servers/@mcpdotdirect/starknet-mcp-server/badge" alt="Starknet Server MCP server" /> </a>The Starknet MCP Server leverages the Model Context Protocol to provide blockchain services to AI agents. It offers a comprehensive interface to the Starknet ecosystem, powering AI assistants with the ability to interact with Starknet blockchain data and operations through natural language.
Key capabilities include:
All services are exposed through a consistent interface of MCP tools and resources, making it easy for AI agents to discover and use Starknet blockchain functionality. Every tool that accepts Starknet addresses also supports StarknetID, automatically resolving human-readable identities to addresses behind the scenes.
The server supports the following Starknet networks:
To install starknet-mcp-server for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install @mcpdotdirect/starknet-mcp-server --client claude
The easiest way to get started is to use npx to run the package directly:
# Run the stdio server without installation
npx @mcpdotdirect/starknet-mcp-server
# Run the HTTP server without installation
npx @mcpdotdirect/starknet-mcp-server http
This will automatically download and run the latest version without needing to install it first.
If you plan to use it frequently, you can install it globally:
# Install globally
npm install -g @mcpdotdirect/starknet-mcp-server
# Then run from anywhere
starknet-mcp-server
starknet-mcp-server http
# Add to your project
npm install @mcpdotdirect/starknet-mcp-server
# Using yarn
yarn add @mcpdotdirect/starknet-mcp-server
# Using pnpm
pnpm add @mcpdotdirect/starknet-mcp-server
Then add to your package.json scripts:
"scripts": {
"starknet-mcp": "starknet-mcp-server",
"starknet-mcp-http": "starknet-mcp-server http"
}
If you want to run from source or develop locally:
# Clone the repository
git clone https://github.com/mcpdotdirect/starknet-mcp-server.git
cd starknet-mcp-server
# Install dependencies
npm install
# Start the stdio server
npm start
# Or start the HTTP server
npm run start:http
For development with auto-reload:
# Development mode with stdio
npm run dev
# Development mode with HTTP
npm run dev:http
The server uses the following default configuration:
These values are hardcoded in the application. If you need to modify them, you can edit the following files:
src/core/chains.tssrc/server/http-server.tsYou can run the Starknet MCP Server in two modes:
# Run the server in stdio mode (for CLI tools and AI assistants)
npx @mcpdotdirect/starknet-mcp-server
# Run the server in HTTP mode (for web applications)
npx @mcpdotdirect/starknet-mcp-server http
The HTTP server runs on port 3000 by default and provides both a REST API and Server-Sent Events (SSE) for real-time communication.
To connect to the Starknet MCP server from Cursor:
Open Cursor and go to Settings (gear icon in the bottom left)
Click on "Features" in the left sidebar
Scroll down to "MCP Servers" section
Click "Add new MCP server"
Enter the following details:
starknet-mcp-servercommandnpx @mcpdotdirect/starknet-mcp-serverClick "Save"
Once connected, you can use the MCP server's capabilities directly within Cursor. The server will appear in the MCP Servers list and can be enabled/disabled as needed.
For a more portable configuration that you can share with your team or use across projects, you can create an .cursor/mcp.json file in your project's root directory:
{
"mcpServers": {
"starknet-mcp-server": {
"command": "npx",
"args": [
"@mcpdotdirect/starknet-mcp-server"
]
},
"starknet-mcp-http": {
"command": "npx",
"args": [
"@mcpdotdirect/starknet-mcp-server",
"http"
]
}
}
}
Place this file in your project's .cursor directory (create it if it doesn't exist), and Cursor will automatically detect and use these MCP server configurations when working in that project.
If you're developing a web application and want to connect to the HTTP server with Server-Sent Events (SSE), you can use this configuration:
{
"mcpServers": {
"starknet-mcp-sse": {
"url": "http://localhost:3000/sse"
}
}
}
If you're using Claude CLI, you can connect to the MCP server with just two commands:
# Add the MCP server using npx
claude mcp add starknet-mcp-server npx @mcpdotdirect/starknet-mcp-server
# Start Claude with the MCP server enabled
claude
After configuring the MCP server, you can easily use it in Cursor. For example:
// starknet-example.js
async function main() {
try {
// When using with Cursor, you can simply ask Cursor to:
// "Check the ETH balance of address 0x049d36570d4e46f48e99674bd3fcc84644ddd6b96f7c741b1562b82f9e004dc7 on Starknet mainnet"
// Or "Lookup the Starknet ID for address 0x049d36570d4e46f48e99674bd3fcc84644ddd6b96f7c741b1562b82f9e004dc7"
// Cursor will use the MCP server to execute these operations
// without requiring any additional code from you
} catch (error) {
console.error("Error:", error.message);
}
}
main();
//
---
Prerequisites
Time Estimate
15-60 minutes depending on server complexity
Steps
Troubleshooting
✓ Do
✗ Don't
💡 Pro Tips
Architecture
Model Context Protocol standardizes how AI hosts (Claude, Cursor) communicate with external tools and data sources through server implementations.
Protocols
Compatibility
✓ Use when
Use when you need Claude to access external data, execute actions, or integrate with tools. Best for extending AI capabilities beyond conversation.
✗ Avoid when
Avoid when native integrations exist (use official APIs directly), for real-time critical systems, or when security/compliance requires zero external dependencies.