Sponsored by Deepsite.site

MCP Server Template (

Created By
bsmi02110 months ago
This template helps you quickly bootstrap a new Model Context Protocol (MCP) server project based on recommended practices.
Content

MCP Server Template (create-mcp-server)

This template helps you quickly bootstrap a new Model Context Protocol (MCP) server project based on recommended practices.

Usage (Creating a New Server)

To create a new MCP server project named my-new-mcp-server, run the following command using npx:

npx create-mcp-server my-new-mcp-server

(Note: If you haven't published this package to npm, you might need to run npm link in this template directory first, then use create-mcp-server my-new-mcp-server)

This will:

  1. Create a new directory named my-new-mcp-server.
  2. Prompt you for project details (name, description).
  3. Copy the template files (src, docs, config files, etc.) into the new directory.
  4. Update the package.json with your project details.

After initialization, follow the instructions provided in the terminal:

cd my-new-mcp-server
npm install
# Review configuration in src/config/ConfigurationManager.ts
# Add your tools in src/tools/
# Add your services in src/services/
npm run dev  # Start the development server

Developing This Template (Advanced)

This section describes the structure and development process for the mcp-server-template itself. You typically don't need this if you are just using the template to create your own server.

Project Structure

  • /src: Contains all source code.
    • /config: Configuration management (ConfigurationManager).
    • /services: Core business logic classes.
    • /tools: MCP tool definitions and adapters (*Tool.ts,*Params.ts).
    • /types: TypeScript interfaces and Zod schemas.
    • /utils: Shared utility functions (logging, errors, etc.).
    • initialize.ts: Server instance creation and tool registration.
    • server.ts: Main application entry point.
  • /dist: Compiled JavaScript output (generated by pm run build).
  • package.json: Project metadata and dependencies.
  • sconfig.json: TypeScript compiler options.
  • .eslintrc.json: ESLint configuration.
  • .prettierrc.json: Prettier configuration.
  • .gitignore: Git ignore rules.

Getting Started

  1. Install Dependencies: ash npm install
  2. Configure Husky (if needed, first time): ash npx husky install
  3. Run in Development Mode: (Uses s-node and odemon for auto-reloading) ash npm run dev
  4. Build for Production: ash npm run build
  5. Run Production Build: ash npm start

Adding a New Tool (yourTool)

  1. Define Types: Create src/types/yourServiceTypes.ts with interfaces (e.g., YourServiceConfig, YourServiceData). Export from src/types/index.ts.
  2. Implement Service: Create src/services/YourService.ts with the core logic class. Export from src/services/index.ts.
  3. Define Tool Params: Create src/tools/yourToolParams.ts with TOOL_NAME, TOOL_DESCRIPTION, and TOOL_PARAMS (using Zod with detailed .describe() calls).
  4. Implement Tool Registration: Create src/tools/yourTool.ts. Import the service and params. Create a function that instantiates the service and calls server.tool() with an async handler that validates input, calls the service, formats output, and handles errors (mapping to McpError).
  5. Register the Tool: Import and call the registration function from src/tools/index.ts within the egisterTools function.
  6. Add Configuration: If needed, update src/config/ConfigurationManager.ts to include config types, defaults, getters, and updaters for the new service.
  7. Add Utilities: If needed, add helper functions to src/utils/ and export them.
  8. Write Tests: Add unit tests for the service logic in src/services/ and potentially integration tests for the tool adapter in src/tools/.

Linting and Formatting

  • Lint: pm run lint
  • Format: pm run format

Code will be automatically linted and formatted on commit via Husky and lint-staged.

Recommend Servers
TraeBuild with Free GPT-4.1 & Claude 3.7. Fully MCP-Ready.
Playwright McpPlaywright MCP server
Howtocook Mcp基于Anduin2017 / HowToCook (程序员在家做饭指南)的mcp server,帮你推荐菜谱、规划膳食,解决“今天吃什么“的世纪难题; Based on Anduin2017/HowToCook (Programmer's Guide to Cooking at Home), MCP Server helps you recommend recipes, plan meals, and solve the century old problem of "what to eat today"
BlenderBlenderMCP connects Blender to Claude AI through the Model Context Protocol (MCP), allowing Claude to directly interact with and control Blender. This integration enables prompt assisted 3D modeling, scene creation, and manipulation.
TimeA Model Context Protocol server that provides time and timezone conversion capabilities. This server enables LLMs to get current time information and perform timezone conversions using IANA timezone names, with automatic system timezone detection.
Visual Studio Code - Open Source ("Code - OSS")Visual Studio Code
Baidu Map百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
MCP AdvisorMCP Advisor & Installation - Use the right MCP server for your needs
MiniMax MCPOfficial MiniMax Model Context Protocol (MCP) server that enables interaction with powerful Text to Speech, image generation and video generation APIs.
Serper MCP ServerA Serper MCP Server
DeepChatYour AI Partner on Desktop
Amap Maps高德地图官方 MCP Server
EdgeOne Pages MCPAn MCP service designed for deploying HTML content to EdgeOne Pages and obtaining an accessible public URL.
Tavily Mcp
AiimagemultistyleA Model Context Protocol (MCP) server for image generation and manipulation using fal.ai's Stable Diffusion model.
ChatWiseThe second fastest AI chatbot™
Jina AI MCP ToolsA Model Context Protocol (MCP) server that integrates with Jina AI Search Foundation APIs.
WindsurfThe new purpose-built IDE to harness magic
CursorThe AI Code Editor
Y GuiA web-based graphical interface for AI chat interactions with support for multiple AI models and MCP (Model Context Protocol) servers.
Zhipu Web SearchZhipu Web Search MCP Server is a search engine specifically designed for large models. It integrates four search engines, allowing users to flexibly compare and switch between them. Building upon the web crawling and ranking capabilities of traditional search engines, it enhances intent recognition capabilities, returning results more suitable for large model processing (such as webpage titles, URLs, summaries, site names, site icons, etc.). This helps AI applications achieve "dynamic knowledge acquisition" and "precise scenario adaptation" capabilities.