mcp-server-patterns

Designs and debugs MCP server implementations for Node and TypeScript projects.

Updated May 17, 2022
One-click install
npx skills add https://github.com/kanade0404/dotfiles --skill mcp-server-patterns-kanade0404
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: mcp-server-patterns
Source: https://github.com/kanade0404/dotfiles/tree/main/.claude-plugin/skills/mcp-server-patterns
Command: npx skills add https://github.com/kanade0404/dotfiles --skill mcp-server-patterns-kanade0404

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps you design, implement, and troubleshoot Model Context Protocol servers without getting lost in changing SDK details or transport choices.

Core Features & Use Cases

  • Tool, resource, and prompt design: Structure server capabilities so clients can invoke actions, read data, and surface reusable prompts cleanly.
  • Transport guidance: Choose and implement the right connection style for local and remote clients, including stdio and Streamable HTTP.
  • SDK upgrade resilience: Work safely across evolving Node and TypeScript MCP APIs by validating current patterns before coding.
  • Use case: A team building a local Claude Desktop server can use this Skill to register tools, validate inputs with schemas, and keep the entrypoint transport-agnostic.

Quick Start

Use the mcp-server-patterns skill to plan or debug your MCP server architecture, select the correct transport, and apply current Node and TypeScript SDK patterns with schema-first validation.

Frequently Asked Questions about mcp-server-patterns

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I build an MCP server with Node and TypeScript?

To build an MCP server with Node and TypeScript, structure server capabilities by registering tools, resources, and prompts, then apply schema-first validation using Zod to ensure inputs are checked cleanly before clients can invoke actions.

What is the difference between stdio and Streamable HTTP for MCP server transport?

MCP server transport choices depend on the client location: stdio is typically for local clients like Claude Desktop, while Streamable HTTP is used for remote clients, with the architecture kept transport-agnostic to support both cleanly.

How do I validate tool inputs in a Model Context Protocol server?

You validate tool inputs in a Model Context Protocol server by applying schema-first tool validation patterns and using Zod-based input checking to ensure current MCP API requirements are satisfied before actions execute.

Can I use this approach to upgrade and troubleshoot existing MCP SDK integrations?

Yes, you can troubleshoot and upgrade MCP SDK integrations by validating current Node and TypeScript API patterns before coding, which helps work safely across evolving SDK details without breaking existing server implementations.

What's the best way to design prompts and resources for an MCP server?

The best way to design prompts and resources for an MCP server is to structure server capabilities so clients can cleanly read data and surface reusable prompts, ensuring the schema-first architecture remains transport-agnostic.

Why do my MCP tools fail to register when using the TypeScript SDK?

MCP tools may fail to register if the implementation does not satisfy current MCP API patterns or schema-first validation requirements, making it necessary to debug the server architecture and validate Node SDK integration details.