広告掲載
MCP.so
ログイン

MCP Server Template

@stevennevins

リポジトリ

基本情報

カテゴリ

開発者ツール

トランスポート

stdio

作者

stevennevins

MCP Server Template について

概要はまだありません

#mcp-server#architect#llm-cli

MCP Server Template 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": {
    "architect-mcp-server": {
      "command": "npx",
      "args": [
        "@modelcontextprotocol/inspector",
        "node",
        "dist/index.js"
      ]
    }
  }
}

MCP Server Template 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。

上のボタンで一時的なサンドボックスでこのサーバーを実行し、ツール一覧を取得できます。

概要

What is MCP Server Template?

MCP Server Template is a starter project for building Model Context Protocol (MCP) servers. It provides a development environment, an Architect tool that integrates with the LLM CLI for architectural design feedback, and built-in testing utilities. The template is intended for developers who want to create MCP servers and need a ready-to-use structure with hot reload, testing, and debugging support.

How to use MCP Server Template?

Install dependencies with npm install, then start development with npm run dev. Build the project with npm run build, run tests with npm test, and start the production server with npm start. For local testing, use the TestClient, MCP Inspector (npx @modelcontextprotocol/inspector node dist/index.js), or integrate with Cursor by building and linking the package.

Key features of MCP Server Template

  • Architect tool for architectural design feedback via LLM CLI
  • Maintains conversation context across multiple LLM interactions
  • Includes TestClient for unit testing of tools
  • MCP Inspector for visual debugging and tool inspection
  • Hot reload development server with npm run dev
  • Integration with Cursor for local MCP server testing

Use cases of MCP Server Template

  • Building a new MCP server from a structured template
  • Getting architectural feedback on designs using the LLM CLI
  • Testing MCP tool implementations with a built-in test client
  • Debugging MCP server communication via the inspector web UI
  • Developing and testing MCP servers locally with Cursor

よくある質問

1

What prerequisites does the template require?

The LLM CLI must be installed and available in your PATH. It can be installed via `brew install llm`.

2

How do I test my tools locally?

Use the TestClient (imported from `./utils/TestClient`) for unit tests, or run the MCP Inspector with `npx @modelcontextprotocol/inspector node dist/index.js` for visual debugging.

3

Can I test the MCP server with Cursor?

Yes. Build the project, run `npm run link`, then add the server to Cursor settings as a command-type MCP server using the linked binary name (`architect-test-mcp-tool`).

4

How do I debug communication issues?

Use the MCP Inspector, which provides a web interface at `http://localhost:5173` to view tools, test calls, and inspect request/response payloads.

5

What dependencies are needed to run the template?

Node.js, npm, and the LLM CLI. The template uses standard npm scripts for installation, development, building, testing, and production.

コメント

「開発者ツール」の他のコンテンツ

FARPY

mangomunchr

Verified distributed compute for humans, applications, and agents. Submit Blender, Octane, and video workloads, route them across qualified GPUs, track asynchronous execution, download finished artifacts, and verify FARP

1

Moxie Docs

Jackalope-Dev

Automated codebase documentation for GitHub: searchable docs, MCP context for AI agents, doc drift detection, and Friday Cleanup PRs.

1

Mcp-Warden

ermoluk

Local-first credential broker for MCP. AI coding agents (Claude Code, Cursor, Codex…) call APIs, SSH and databases through scoped presets; secrets stay in your OS keychain and never enter the agent's context.

4

Vibgrate MCP

Vibgrate

Query your team's drift, vulnerability, and migration data from any AI assistant. Vibgrate MCP connects Cursor, Claude, ChatGPT, Windsurf, or VS Code to Vibgrate Cloud: 51 tools for DriftScores, CVEs and EOL runtimes, up

3

GripForge

gripforgeai

The tools your AI needs to make your games. Turn prompts into production-ready game assets — animated characters with their weapons attached, seamless textures, terrain, VFX, HUDs — and playable game kits Unity, Godot, U

1
広告掲載