広告掲載
MCP.so
ログイン

@sinco Lab/evm MCP Server

@sinco-lab

リポジトリ

基本情報

カテゴリ

その他

トランスポート

stdio

作者

sinco-lab

@sinco Lab/evm MCP Server について

An EVM interaction service based on Model Context Protocol (MCP)

@sinco Lab/evm 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": {
    "evm-mcp-server-sinco-lab": {
      "command": "node",
      "args": [
        "build/evm.js"
      ]
    }
  }
}

@sinco Lab/evm MCP Server のツール

ツール一覧はまだありません

この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

What is @sinco-lab/evm-mcp-server?

An EVM interaction service gateway based on Model Context Protocol (MCP) and Viem, enabling AI agents or services to securely interact with a configured EVM-compatible blockchain.

How to use @sinco-lab/evm-mcp-server?

Install dependencies with pnpm install, build with pnpm run build, then configure environment variables (WALLET_PRIVATE_KEY, RPC_PROVIDER_URL) in a .env file or directly in a client’s MCP server config. Run the server using node build/evm.js or configure clients like Cursor or Claude Desktop to launch it automatically.

Key features of @sinco-lab/evm-mcp-server

  • Exposes EVM functionalities as standard MCP tools.
  • Uses the modern Viem library for reliable EVM interactions.
  • Connects to any EVM-compatible chain via configurable RPC URL.
  • Provides tools for balances, transfers, token operations, and message signing.
  • Developed entirely in TypeScript for type safety and maintainability.

Use cases of @sinco-lab/evm-mcp-server

  • AI agents performing on-chain transactions like token transfers.
  • Querying wallet balances and token allowances programmatically.
  • Signing messages or approving token spenders via AI-driven workflows.
  • Automating approval and token transfer operations in dApp bots.
  • Enabling chatbots or virtual assistants to interact with EVM blockchains.

よくある質問

1

What is the purpose of @sinco-lab/evm-mcp-server?

It acts as a gateway for AI agents or MCP clients to securely interact with EVM-compatible blockchains, exposing blockchain operations as standardized MCP tools.

2

What dependencies are required to run the server?

Node.js version 18.0.0 or higher and the pnpm package manager are required.

3

How are blockchain credentials configured?

The server uses environment variables `WALLET_PRIVATE_KEY` (the wallet’s private key) and `RPC_PROVIDER_URL` (the JSON‑RPC endpoint). These can be placed in a `.env` file or directly in the MCP client’s configuration file.

4

Which EVM operations does the server support?

The server exposes tools for checking balances, sending native tokens, transferring ERC20 tokens, signing messages, getting token allowances, approving/revoking allowances, and more – a full list is available in the README.

5

How should private keys be managed for security?

It is strongly recommended to use a dedicated wallet for testing. Never commit private keys to version control, and avoid placing them directly in configuration files (e.g., `.cursor/mcp.json`) for high‑value environments.

コメント

「その他」の他のコンテンツ

Yuppsy

Yuppsy MCP: build and publish real estate websites from your AI assistant. Yuppsy lets your AI assistant create live websites for real estate agents and individual property listings. You don't need a designer or any code

🚀 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

FastMCP v2 🚀

jlowin

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

26.0K

Figs, Relationship Expert

Figs O'Sullivan, LMFT

Couples therapist Figs O'Sullivan (LMFT, 17 years, endorsed by Sue Johnson, creator of EFT) inside your AI. Ask relationship questions answered from his clinical writing, name the pattern in a fight, get a three-step rep

Hindsight

vectorize-io

Hindsight: Agent Memory That Learns

50.4K
広告掲載