typescript-mcp-server-generator

$npx mdskill add github/awesome-copilot/typescript-mcp-server-generator

Generate a complete TypeScript MCP server project using the v2 SDK.

  • Solves the need for a scaffolded MCP server with tools and resources.
  • Depends on @modelcontextprotocol/server, core, node, and zod v4.
  • Selects HTTP or stdio transport based on user requirements.
  • Outputs a full project with configuration and package setup.

SKILL.md

.github/skills/typescript-mcp-server-generatorView on GitHub ↗
---
name: typescript-mcp-server-generator
description: 'Generate a complete MCP server project in TypeScript using the MCP TypeScript SDK v2 (@modelcontextprotocol/server) with tools, resources, and proper configuration'
---

# Generate TypeScript MCP Server

Create a complete Model Context Protocol (MCP) server in TypeScript using the **MCP TypeScript SDK v2** with the following specifications:

## Requirements

1. **Project Structure**: Create a new TypeScript/Node.js project with proper directory structure
2. **NPM Packages**: The v1 monolithic `@modelcontextprotocol/sdk` package is retired. Use the focused v2 packages:
   - `@modelcontextprotocol/server` — server implementation (stdio transport via the `@modelcontextprotocol/server/stdio` subpath)
   - `@modelcontextprotocol/node` — Node HTTP transport (`NodeStreamableHTTPServerTransport`), or a framework adapter: `@modelcontextprotocol/express`, `@modelcontextprotocol/hono`, `@modelcontextprotocol/fastify` — each adapter requires its peer framework to be installed alongside it (e.g. `@modelcontextprotocol/express` + `express`)
   - `@modelcontextprotocol/core` — shared protocol schemas (import `*Schema` constants from here, not from `sdk/types.js`)
   - `zod@^4.2` — v2 requires Zod 4.2+; do not use zod@3
3. **Runtime**: Node.js 20+ (v2 minimum); ESM-first with `"type": "module"` (a CommonJS build is also shipped, so `require()` works if needed)
4. **Server Type**: Choose between HTTP (Streamable HTTP transport) or stdio-based server. SSE and WebSocket transports were removed in v2 — do not generate them.
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/server`, `zod@^4.2`, and the transport package — `@modelcontextprotocol/node` for plain Node HTTP, or a framework adapter together with its peer framework (e.g. `npm install @modelcontextprotocol/express express`)
- 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 from `@modelcontextprotocol/server` for high-level implementation
- Set server name and version
- Choose the appropriate transport:
  - HTTP (Node): `NodeStreamableHTTPServerTransport` from `@modelcontextprotocol/node`
  - HTTP (Web Standard runtimes): `WebStandardStreamableHTTPServerTransport` from `@modelcontextprotocol/server`
  - stdio: `StdioServerTransport` from `@modelcontextprotocol/server/stdio`
- For HTTP: prefer a framework adapter (`@modelcontextprotocol/express`, etc.) with proper middleware and error handling
- Note that v2 uses Web Standard `Headers`/`Request` types; read headers with `ctx.http?.req?.headers.get('x-custom')`

### Tool Implementation
- Use `registerTool()` with a config object — v1 variadic `.tool()` signatures are gone:
  ```typescript
  server.registerTool('greet', {
    description: 'Greet user',
    inputSchema: z.object({ name: z.string() })
  }, async ({ name }, ctx) => {
    return { content: [{ type: 'text', text: `Hello, ${name}!` }] };
  });
  ```
- Schemas must be full Zod objects (`z.object({...})`) — raw shape objects (`{ name: z.string() }`) are deprecated
- Provide clear `title` and `description` fields
- Return both `content` and `structuredContent` in results
- The handler's second parameter is a structured `ctx` object (replaces v1 `extra`): `ctx.mcpReq.signal`, `ctx.mcpReq.id`, `ctx.mcpReq.send(...)`, `ctx.mcpReq.notify(...)`
- Implement proper error handling with try-catch blocks; use the v2 error hierarchy (`ProtocolError`, `SdkError`, `SdkHttpError` with `.status`) instead of v1 `McpError`/`StreamableHTTPError`
- 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 (same config-object style as `registerTool()`)
- Consider adding completion support for better UX; note the v2 `completable()` wrapper order: `completable(z.string(), callback).optional()` (optional applied outside)

### 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 (LLM-assisted via the multi-round `input_required` pattern)
- 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
  - Strict `Content-Type` handling: v2 rejects non-`application/json` POST bodies
  
- **For stdio Servers**:
  - Proper stdin/stdout handling
  - Environment-based configuration
  - Process lifecycle management

## Migrating an Existing v1 Server
- Run the official codemod first: `npx @modelcontextprotocol/codemod@latest v1-to-v2 .`
- Then search for `@mcp-codemod-error` markers for the parts requiring manual judgment (transport choice, header reads, error classification)
- Swap `McpError + ErrorCode` checks for the new error classes; HTTP status now lives on `error.status`, not `error.code`
- `Server.createMessage()`, `listRoots()`, `sendLoggingMessage()` and the `roots`/`sampling`/`logging` capability fields are deprecated in v2 — avoid them in new code

## 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
- LLM-powered tools using the multi-round `input_required` pattern (the v2 replacement for the deprecated sampling subsystem)
- 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.

More from github/awesome-copilot

SkillDescription
acquire-codebase-knowledgeUse this skill when the user explicitly asks to map, document, or onboard into an existing codebase. Trigger for prompts like "map this codebase", "document this architecture", "onboard me to this repo", or "create codebase docs". Do not trigger for routine feature implementation, bug fixes, or narrow code edits unless the user asks for repository-level discovery.
acreadiness-assessRun the AgentRC readiness assessment on the current repository and produce a static HTML dashboard at reports/index.html. Wraps `npx github:microsoft/agentrc readiness` and hands off rendering to the @ai-readiness-reporter custom agent. Supports policies (--policy) for org-specific scoring. Use when asked to assess, audit, or score the AI readiness of a repo.
acreadiness-generate-instructionsGenerate tailored AI agent instruction files via AgentRC instructions command. Produces .github/copilot-instructions.md (default, recommended for Copilot in VS Code) plus optional per-area .instructions.md files with applyTo globs for monorepos. Use after running /acreadiness-assess to close gaps in the AI Tooling pillar.
acreadiness-policyHelp the user pick, write, or apply an AgentRC policy. Policies customise readiness scoring by disabling irrelevant checks, overriding impact/level, setting pass-rate thresholds, or chaining org baselines with team overrides. Use when the user asks about strict mode, AI-only scoring, custom weights, CI gating, or wants org-wide standardisation.
ad-campaign-analyzerUse this skill when the user shares ad campaign performance data and asks what to cut, scale, or test. Trigger for prompts like "analyze my ad campaigns", "where am I wasting ad spend", "reallocate my ad budget", "which ads are actually working", or "ROAS analysis". Do not trigger for campaign planning or creative generation without performance data.
add-educational-comments'Add educational comments to the file specified, or prompt asking for file to comment if one is not provided.'
adobe-illustrator-scriptingWrite, debug, and optimize Adobe Illustrator automation scripts using ExtendScript (JavaScript/JSX). Use when creating or modifying scripts that manipulate documents, layers, paths, text frames, colors, symbols, artboards, or any Illustrator DOM objects. Covers the complete JavaScript object model, coordinate system, measurement units, export workflows, and scripting best practices.
agent-architectureDesign AI agent architectures through requirements discovery, or audit and diagnose architectural flaws in existing agents. Architecture only; excludes implementation and general code review.
agent-governance|
agent-owasp-compliance|