New to Claude Skills? Learn how to install them →

affaan-m on GitHub

MCP Server Patterns

Free

Streamline your MCP server development with essential tools.

Get this skill

Free · Opens the source repo

What MCP Server Patterns does

MCP Server Patterns is designed for developers working with the Model Context Protocol (MCP), providing a structured approach to building and maintaining MCP servers using Node and TypeScript. This skill facilitates the integration of tools, resources, and prompts that AI assistants can utilize, ensuring a seamless interaction between your server and AI clients. By leveraging the SDK API, users can stay up-to-date with the evolving capabilities of MCP, making it easier to implement new features or troubleshoot existing setups.

The core functionality revolves around the registration of tools, resources, and prompts. Developers can define actions that AI models can invoke, set up read-only data sources, and create reusable prompt templates. The skill emphasizes the importance of understanding the transport mechanisms available, such as stdio for local clients and Streamable HTTP for remote interactions. This flexibility allows developers to adapt their server architecture based on the specific needs of their applications and clients.

Best practices are highlighted throughout the skill, guiding users on how to structure their server logic and manage input validation effectively using Zod. The skill encourages a schema-first approach to ensure that all tools are well-defined, with clear documentation on parameters and expected return types. Additionally, it addresses common pitfalls, such as error handling and versioning, helping developers maintain robust and reliable MCP servers.

Whether you're implementing a new MCP server or upgrading an existing one, MCP Server Patterns provides the resources and guidance necessary to navigate the complexities of server development in the context of AI integration. This skill is particularly useful for those looking to enhance their MCP server capabilities or streamline their development process.

When to use it

Use this skill when setting up a new MCP server, adding new tools or resources, or when troubleshooting transport issues.

When not to use it

This skill may not be suitable for users unfamiliar with Node or TypeScript, or those seeking a non-programmatic approach to server management.

What you can build with it

Setting Up a New MCP Server

Quickly implement a new MCP server using the provided Node/TypeScript SDK and best practices.

Integrating New Tools

Easily add new tools and resources to your existing MCP server to enhance its capabilities.

Troubleshooting Transport Issues

Utilize the skill to identify and resolve common transport-related problems when connecting AI clients.

How to install MCP Server Patterns

View source

1. Install with the skills CLI

npx skills add affaan-m/ecc/mcp-server-patterns --agent claude-code

2. Or install it manually

Download the skill folder and drop it into ~/.claude/skills/ for all projects, or .claude/skills/ to scope it to one repo. Restart Claude Code so it picks up the new skill.

Anthropic's agentic coding CLI, and the reference implementation of Agent Skills. Drop a skill folder into ~/.claude/skills and Claude Code loads it automatically whenever a task matches the skill's description. Claude Code docs

Inside SKILL.md

Written by affaan-m

MCP Server Patterns

The Model Context Protocol (MCP) lets AI assistants call tools, read resources, and use prompts from your server. Use this skill when building or maintaining MCP servers. The SDK API evolves; check Context7 (query-docs for "MCP") or the official MCP documentation for current method names and signatures.

When to Use

Use when: implementing a new MCP server, adding tools or resources, choosing stdio vs HTTP, upgrading the SDK, or debugging MCP registration and transport issues.

How It Works

Core concepts

  • Tools: Actions the model can invoke (e.g. search, run a command). Register with registerTool() or tool() depending on SDK version.
  • Resources: Read-only data the model can fetch (e.g. file contents, API responses). Register with registerResource() or resource(). Handlers typically receive a uri argument.
  • Prompts: Reusable, parameterised prompt templates the client can surface (e.g. in Claude Desktop). Register with registerPrompt() or equivalent.
  • Transport: stdio for local clients (e.g. Claude Desktop); Streamable HTTP is preferred for remote (Cursor, cloud). Legacy HTTP/SSE is for backward compatibility.

The Node/TypeScript SDK may expose tool() / resource() or registerTool() / registerResource(); the official SDK has changed over time. Always verify against the current MCP docs or Context7.

Connecting with stdio

For local clients, create a stdio transport and pass it to your server’s connect method. The exact API varies by SDK version (e.g. constructor vs factory). See the official MCP documentation or query Context7 for "MCP stdio server" for the current pattern.

Keep server logic (tools + resources) independent of transport so you can plug in stdio or HTTP in the entrypoint.

Remote (Streamable HTTP)

For Cursor, cloud, or other remote clients, use Streamable HTTP (single MCP HTTP endpoint per current spec). Support legacy HTTP/SSE only when backward compatibility is required.

Examples

Install and server setup

npm install @modelcontextprotocol/sdk zod
import { McpServer } from "@modelcontextprotocol/sdk/server/mcp.js";
import { z } from "zod";

const server = new McpServer({ name: "my-server", version: "1.0.0" });

Register tools and resources using the API your SDK version provides: some versions use server.tool(name, description, schema, handler) (positional args), others use server.tool({ name, description, inputSchema }, handler) or registerTool(). Same for resources — include a uri in the handler when the API provides it. Check the official MCP docs or Context7 for the current @modelcontextprotocol/sdk signatures to avoid copy-paste errors.

Use Zod (or the SDK’s preferred schema format) for input validation.

Best Practices

  • Schema first: Define input schemas for every tool; document parameters and return shape.
  • Errors: Return structured errors or messages the model can interpret; avoid raw stack traces.
  • Idempotency: Prefer idempotent tools where possible so retries are safe.
  • Rate and cost: For tools that call external APIs, consider rate limits and cost; document in the tool description.
  • Versioning: Pin SDK version in package.json; check release notes when upgrading.

Official SDKs and Docs

  • JavaScript/TypeScript: @modelcontextprotocol/sdk (npm). Use Context7 with library name "MCP" for current registration and transport patterns.
  • Go: Official Go SDK on GitHub (modelcontextprotocol/go-sdk).
  • C#: Official C# SDK for .NET.

Frequently asked questions about MCP Server Patterns

Similar skills