How does this skill handle SDK version changes?

The skill emphasizes checking Context7 or official MCP documentation for current method signatures and recommends pinning SDK versions in your project configuration to avoid breaking changes.

When should I use Streamable HTTP instead of stdio transport?

Use stdio for local clients like Claude Desktop. Streamable HTTP is the preferred transport for remote clients, cloud deployments, and integrations with IDEs like Cursor.

What is the Model Context Protocol (MCP)?

MCP is an open standard that allows AI assistants like Claude to securely connect to external tools, data sources, and resources through a standardized server interface.

Why is Zod recommended for MCP server development?

Zod allows you to define clear input schemas for your tools, ensuring that the AI model provides correctly formatted data and helping to prevent runtime errors.

Does this skill support languages other than TypeScript?

Yes, while the core examples focus on the Node/TypeScript SDK, it also provides implementation patterns and references for official Go and C# MCP SDKs.

MCP Server Patterns

Name: MCP Server Patterns
Author: lyxjack

bylyxjack

•

API開発

Streamlines the development of Model Context Protocol (MCP) servers with standardized implementation patterns for tools, resources, and transport layers.

This skill provides comprehensive guidance for building and maintaining MCP servers using the Node/TypeScript SDK and other official libraries. It simplifies the process of creating tools for AI actions, read-only resources, and parameterized prompts while ensuring robust data handling through Zod validation. Whether you are implementing local stdio connections for Claude Desktop or remote Streamable HTTP for cloud environments like Cursor, this skill helps you follow current best practices and official SDK specifications to create reliable AI-to-backend integrations.

主な機能

01Implementation guidance for both stdio and Streamable HTTP transports

021 GitHub stars

03Zod-based schema validation for robust tool input handling

04Best practices for error handling, idempotency, and rate limiting

05Architecture patterns for TypeScript, Go, and C# SDKs

06Standardized tool, resource, and prompt registration patterns

ユースケース

01Building custom MCP servers to extend Claude Desktop capabilities

02Deploying remote MCP servers for cloud-based AI coding environments

03Standardizing API integration for AI agents through structured schemas

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add lyxjack/toolbox mcp-server-patterns

For use in Claude.ai and ChatGPT

主な機能

01Implementation guidance for both stdio and Streamable HTTP transports

021 GitHub stars

03Zod-based schema validation for robust tool input handling

04Best practices for error handling, idempotency, and rate limiting

05Architecture patterns for TypeScript, Go, and C# SDKs

06Standardized tool, resource, and prompt registration patterns

ユースケース

01Building custom MCP servers to extend Claude Desktop capabilities

02Deploying remote MCP servers for cloud-based AI coding environments

03Standardizing API integration for AI agents through structured schemas

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add lyxjack/toolbox mcp-server-patterns

For use in Claude.ai and ChatGPT