Skill

mcp-server-patterns

Build MCP servers with Node/TypeScript SDK -- tools, resources, prompts, Zod validation, stdio vs Streamable HTTP.

npx claudepluginhub nassimbf/ftitos-claude-code

Tool Access

This skill uses the workspace's default tool permissions.

Preview

The Model Context Protocol (MCP) lets AI assistants call tools, read resources, and use prompts from your server.

SKILL.md

Similar Skills

cache-components

139.3k

Expert guidance for Next.js Cache Components and Partial Prerendering (PPR). **PROACTIVE ACTIVATION**: Use this skill automatically when working in Next.js projects that have `cacheComponents: true` in their next.config.ts/next.config.js. When this config is detected, proactively apply Cache Components patterns and best practices to all React Server Component implementations. **DETECTION**: At the start of a session in a Next.js project, check for `cacheComponents: true` in next.config. If enabled, this skill's patterns should guide all component authoring, data fetching, and caching decisions. **USE CASES**: Implementing 'use cache' directive, configuring cache lifetimes with cacheLife(), tagging cached data with cacheTag(), invalidating caches with updateTag()/revalidateTag(), optimizing static vs dynamic content boundaries, debugging cache issues, and reviewing Cache Component implementations.

cache-components

mcp-builder

124.2k

Guides building MCP servers enabling LLMs to interact with external services via tools. Covers best practices, TypeScript/Node (MCP SDK), Python (FastMCP).

9 files

anthropics-skills-13

Stats

Stars2

Forks0

Last CommitApr 18, 2026

Actions

View Source View Plugin View on GitHub View README

Help us improve

Share bugs, ideas, or general feedback.

MCP Server Patterns

The Model Context Protocol (MCP) lets AI assistants call tools, read resources, and use prompts from your server.

When to Use

Implementing a new MCP server

Adding tools or resources to an existing server

Choosing stdio vs HTTP transport

Debugging MCP registration and transport issues

Core Concepts

Tools: Actions the model can invoke (e.g. search, run a command)

Resources: Read-only data the model can fetch (e.g. file contents, API responses)

Prompts: Reusable, parameterized prompt templates

Transport: stdio for local clients; Streamable HTTP for remote

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. The SDK API evolves -- check the official MCP documentation or Context7 for current method signatures.

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

Transport

stdio: For local clients (e.g. Claude Desktop). Keep server logic independent of transport.

Streamable HTTP: For remote clients (Cursor, cloud). Support legacy HTTP/SSE only when backward compatibility is required.

Best Practices

Schema first: Define input schemas for every tool; document parameters and return shape

Errors: Return structured errors 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

Versioning: Pin SDK version in package.json; check release notes when upgrading

Official SDKs

JavaScript/TypeScript: @modelcontextprotocol/sdk (npm)

Go: modelcontextprotocol/go-sdk (GitHub)

C#: Official C# SDK for .NET