Sensei MCP Server

@dojoengine

リポジトリ

基本情報

カテゴリ

その他

ライセンス

MIT

トランスポート

stdio

作者

dojoengine

Sensei MCP Server について

Sensei MCP is a Model Context Protocol (MCP) server that provides expert guidance for Dojo and Cairo development on Starknet.

Sensei MCP Server の設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "sensei-mcp": {
      "command": "npx",
      "args": [
        "github:dojoengine/sensei-mcp"
      ]
    }
  }
}

Sensei MCP Server のツール

Beginner-friendly introduction to Dojo development

Essential guidance for configuring Dojo projects

Expert guidance on implementing Dojo systems and game logic

Specialized guidance for creating and working with Dojo models

Comprehensive guide for writing tests for Dojo applications

Detailed guidance on implementing token standards in Dojo

概要

What is Sensei MCP?

Sensei MCP is a Model Context Protocol (MCP) server that provides expert guidance for Dojo and Cairo development on Starknet. It serves as a personal Dojo Sensei, offering specialized knowledge and assistance for building onchain worlds using the Dojo Entity Component System (ECS) framework.

How to use Sensei MCP?

Install via Cursor IDE by adding a new MCP server with the command npx github:dojoengine/sensei-mcp, or add it to Claude Code with claude mcp add sensei-mcp npx github:dojoengine/sensei-mcp. You can also run it directly in the terminal with npx github:dojoengine/sensei-mcp.

Key features of Sensei MCP

Expert guidance for Cairo’s ownership, memory, and type systems
Dojo ECS architecture: Models, Systems, and World patterns
Smart contract development best practices for Starknet
Specialized tools for models, systems, testing, and more
Incremental development workflow from setup through testing
Automated tool selection based on user requests

Use cases of Sensei MCP

Building onchain worlds using the Dojo ECS framework
Writing Cairo smart contracts for Starknet
Setting up Dojo project structure with sozo init
Creating and configuring Dojo models and systems
Writing and running tests for Dojo applications

よくある質問

How do I install Sensei MCP in Cursor?

Open Cursor Settings, navigate to MCP Tools, click “New MCP Server,” and add the configuration with the command `npx github:dojoengine/sensei-mcp` to `mcp.json`. You may need to run the command manually in terminal first.

How do I add Sensei MCP to Claude Code?

Run `claude mcp add sensei-mcp npx github:dojoengine/sensei-mcp` in your terminal.

What specialized tools does Sensei MCP provide?

It provides `dojo_101` (intro), `dojo_config` (project configuration), `dojo_logic` (systems and game logic), `dojo_model` (model creation), `dojo_test` (testing), and `dojo_token` (token standards).

What is the recommended development workflow?

Follow an incremental approach: start with project setup (dojo_101), define models (dojo_model), implement systems (dojo_logic), configure the project (dojo_config), and add tests (dojo_test).

Can I build Sensei MCP from source?

Yes. Clone the repository, run `npm install`, `npm run build`, and `npm start`. The source is at `github.com/dojoengine/sensei-mcp`.

「その他」の他のコンテンツ

FastMCP v2 🚀

jlowin

🚀 The fast, Pythonic way to build MCP servers and clients.

26.0K

LoadOptimizer

LoadOptimizer plans truck, container and pallet loads with a real optimization engine, straight from your AI assistant. Describe the order in plain language, for example "plan 36 Euro pallets on a standard 13.6 m trailer

Blender

ahujasid

Open-source MCP to use Blender with any LLM

23.6K

Klarix Intelligence Engine

Klarix

B2B competitive intelligence, live sales battlecards, 5-axis ICP prospect fit scoring, and tech stack teardowns over MCP and REST with cited public-web evidence.

🚀 Model Context Protocol (MCP) Curriculum for Beginners

microsoft

This open-source curriculum introduces the fundamentals of Model Context Protocol (MCP) through real-world, cross-language examples in .NET, Java, TypeScript, JavaScript, Rust and Python. Designed for developers, it focuses on practical techniques for building modular, scalable,

16.7K