PluginBench
Skill
Official
Pass
Audit score 90

typescript-mcp-server-generator

github/awesome-copilot

Generate a complete, production-ready MCP server in TypeScript with tools, resources, and proper configuration.

What is typescript-mcp-server-generator?

This skill creates a fully functional Model Context Protocol (MCP) server in TypeScript with proper project structure, transport configuration (HTTP or stdio), and tool/resource registration. Use it when you need to build a new MCP server that integrates with Claude or other MCP clients.

  • Sets up a complete TypeScript/Node.js project with MCP SDK and dependencies
  • Configures either HTTP (Express-based) or stdio transport for the server
  • Implements tools with Zod schema validation and error handling
  • Optionally adds resources and prompts with dynamic URI support
  • Includes TypeScript configuration with ES modules support
  • Provides comprehensive error handling and async/await patterns

How to install typescript-mcp-server-generator

npx skills add https://github.com/github/awesome-copilot --skill typescript-mcp-server-generator
Prerequisites
  • Node.js and npm installed
  • Basic TypeScript knowledge
  • Understanding of Model Context Protocol concepts
  • For HTTP servers: familiarity with Express.js (optional)
Claude Code
Cursor
Windsurf
Cline

How to use typescript-mcp-server-generator

  1. 1.Run the install command to add the skill
  2. 2.Choose between HTTP or stdio transport based on your use case
  3. 3.Define your tool schemas using Zod for input/output validation
  4. 4.Implement tool handlers with proper error handling and async support
  5. 5.Configure environment variables for server settings (port, API keys, etc.)
  6. 6.Run the server with `npm start` or `npx tsx server.ts`
  7. 7.Test using MCP Inspector: `npx @modelcontextprotocol/inspector`
  8. 8.Connect the server URL or stdio process to your MCP client

Use cases

Good for
  • Building a custom MCP server to expose internal APIs or tools to Claude
  • Creating a data processing server that transforms or analyzes information
  • Integrating external services (databases, APIs) as MCP tools
  • Setting up a file system or knowledge base server for document analysis
  • Developing an interactive workflow server with user input elicitation
Who it's for
  • Backend developers building MCP integrations
  • Teams creating custom Claude extensions
  • Developers integrating external services with AI agents
  • Engineers setting up local or remote MCP servers

typescript-mcp-server-generator FAQ

Should I use HTTP or stdio transport?

Use HTTP for remote/browser clients and better isolation; use stdio for local integrations with Claude or Cursor where stdin/stdout piping is available.

How do I add multiple tools to my server?

Call `registerTool()` multiple times with different tool names, descriptions, and Zod schemas. Each tool gets its own handler function.

Can I add resources and prompts in addition to tools?

Yes, use `registerResource()` for dynamic resources with ResourceTemplate URIs and `registerPrompt()` for reusable prompts with argument schemas.

How do I handle errors in tools?

Wrap tool logic in try-catch blocks and return structured error responses. Use Zod validation to catch schema mismatches before execution.

How do I test my MCP server?

Use the MCP Inspector tool (`npx @modelcontextprotocol/inspector`) to connect and test tools interactively, or invoke tools directly in your MCP client.

Full instructions (SKILL.md)

Source of truth, from github/awesome-copilot.


name: typescript-mcp-server-generator description: 'Generate a complete MCP server project in TypeScript with tools, resources, and proper configuration'

Generate TypeScript MCP Server

Create a complete Model Context Protocol (MCP) server in TypeScript with the following specifications:

Requirements

  1. Project Structure: Create a new TypeScript/Node.js project with proper directory structure
  2. NPM Packages: Include @modelcontextprotocol/sdk, zod@3, and either express (for HTTP) or stdio support
  3. TypeScript Configuration: Proper tsconfig.json with ES modules support
  4. Server Type: Choose between HTTP (with Streamable HTTP transport) or stdio-based server
  5. Tools: Create at least one useful tool with proper schema validation
  6. Error Handling: Include comprehensive error handling and validation

Implementation Details

Project Setup

  • Initialize with npm init and create package.json
  • Install dependencies: @modelcontextprotocol/sdk, zod@3, and transport-specific packages
  • Configure TypeScript with ES modules: "type": "module" in package.json
  • Add dev dependencies: tsx or ts-node for development
  • Create proper .gitignore file

Server Configuration

  • Use McpServer class for high-level implementation
  • Set server name and version
  • Choose appropriate transport (StreamableHTTPServerTransport or StdioServerTransport)
  • For HTTP: set up Express with proper middleware and error handling
  • For stdio: use StdioServerTransport directly

Tool Implementation

  • Use registerTool() method with descriptive names
  • Define schemas using zod for input and output validation
  • Provide clear title and description fields
  • Return both content and structuredContent in results
  • Implement proper error handling with try-catch blocks
  • Support async operations where appropriate

Resource/Prompt Setup (Optional)

  • Add resources using registerResource() with ResourceTemplate for dynamic URIs
  • Add prompts using registerPrompt() with argument schemas
  • Consider adding completion support for better UX

Code Quality

  • Use TypeScript for type safety
  • Follow async/await patterns consistently
  • Implement proper cleanup on transport close events
  • Use environment variables for configuration
  • Add inline comments for complex logic
  • Structure code with clear separation of concerns

Example Tool Types to Consider

  • Data processing and transformation
  • External API integrations
  • File system operations (read, search, analyze)
  • Database queries
  • Text analysis or summarization (with sampling)
  • System information retrieval

Configuration Options

  • For HTTP Servers:

    • Port configuration via environment variables
    • CORS setup for browser clients
    • Session management (stateless vs stateful)
    • DNS rebinding protection for local servers
  • For stdio Servers:

    • Proper stdin/stdout handling
    • Environment-based configuration
    • Process lifecycle management

Testing Guidance

  • Explain how to run the server (npm start or npx tsx server.ts)
  • Provide MCP Inspector command: npx @modelcontextprotocol/inspector
  • For HTTP servers, include connection URL: http://localhost:PORT/mcp
  • Include example tool invocations
  • Add troubleshooting tips for common issues

Additional Features to Consider

  • Sampling support for LLM-powered tools
  • User input elicitation for interactive workflows
  • Dynamic tool registration with enable/disable capabilities
  • Notification debouncing for bulk updates
  • Resource links for efficient data references

Generate a complete, production-ready MCP server with comprehensive documentation, type safety, and error handling.