typescript-mcp-server-generator作者: github

Complete TypeScript MCP server project generator with tools, resources, and transport configuration. Scaffolds a full Node.js/TypeScript project with @modelcontextprotocol/sdk, zod validation, and choice of HTTP (Express) or stdio transport Generates at least one production-ready tool with schema validation, error handling, and structured content responses Includes tsconfig.json with ES modules, proper package.json setup, and dev tooling (tsx/ts-node) Optionally adds resources with dynamic...

npx skills add https://github.com/github/awesome-copilot --skill typescript-mcp-server-generator

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.

來自 github 的更多技能

console-rendering
by github
Instructions for using the struct tag-based console rendering system in Go
acquire-codebase-knowledge
by github
Use this skill when the user explicitly asks to map, document, or onboard into an existing codebase. Trigger for prompts like "map this codebase", "document…
acreadiness-assess
by github
Run the AgentRC readiness assessment on the current repository and produce a static HTML dashboard at reports/index.html. Wraps `npx github:microsoft/agentrc…
acreadiness-generate-instructions
by github
Generate tailored AI agent instruction files via AgentRC instructions command. Produces .github/copilot-instructions.md (default, recommended for Copilot in VS…
acreadiness-policy
by github
Help the user pick, write, or apply an AgentRC policy. Policies customise readiness scoring by disabling irrelevant checks, overriding impact/level, setting…
add-educational-comments
by github
Add educational comments to code files to transform them into effective learning resources. Adapts explanation depth and tone to three configurable knowledge levels: beginner, intermediate, and advanced Automatically requests a file if none is provided, with numbered list matching for quick selection Expands files by up to 125% using educational comments only (hard limit: 400 new lines; 300 for files over 1,000 lines) Preserves file encoding, indentation style, syntax correctness, and...
adobe-illustrator-scripting
by github
Write, debug, and optimize Adobe Illustrator automation scripts using ExtendScript (JavaScript/JSX). Use when creating or modifying scripts that manipulate…
agent-governance
by github
Declarative policies, intent classification, and audit trails for controlling AI agent tool access and behavior. Composable governance policies define allowed/blocked tools, content filters, rate limits, and approval requirements — stored as configuration, not code Semantic intent classification detects dangerous prompts (data exfiltration, privilege escalation, prompt injection) before tool execution using pattern-based signals Tool-level governance decorator enforces policies at function...

NotebookLM 網頁匯入器

一鍵將網頁和 YouTube 影片匯入 NotebookLM。超過 200,000 位使用者信賴。

安裝 Chrome 擴充功能