$ ~/registry/skill/affaan-m-mcp-server-patterns

SKILL

mcp-server-patterns

Name: mcp-server-patterns
Author: affaan-m

Build MCP servers and tools with Node/TypeScript using current SDK patterns.

Stars

★ 243,958

Source

GitHub

Updated

2026-08-28

// securityCaution

Prompt only, no code
Open source
Community-trusted· 210.5k

Summary

The material indicates this is essentially prompt/documentation content about building MCP servers, with no declared secrets, remote endpoints, or local execution behavior by itself. Given the open-source source and very strong community adoption, overall risk is low, though actual implementations built from it may later introduce permissions, network, or dependency exposure.

CredentialsLow risk

The material explicitly states that no keys or environment variables are required; the README also does not ask for login, API tokens, or credential injection. For this skill itself, there is no visible sign of credential collection, storage, or misuse.

Network egressLow risk

Both the system checks and the material show no predefined remote endpoints. The content only discusses patterns such as stdio and Streamable HTTP as documentation, with no evidence that the skill itself sends user data outward.

Code executionLow risk

This object is classified as prompt-only; the provided content is pattern guidance and example snippets rather than an executable tool. While the examples mention that MCP tools may run commands, that is a general concept and does not mean this skill itself has execution privileges.

Data accessLow risk

There is no declared ability to read or write local files, system resources, or external data sources. The README's discussion of resources remains conceptual, and this skill itself does not appear to request excessive data access.

Supply chainCaution

The source is an open-source GitHub repository with extremely high community stars, which materially lowers risk and improves auditability. However, the license is unspecified, maintenance status is unknown, and the material references npm dependencies such as `@modelcontextprotocol/sdk` and `zod`, so basic supply-chain review is still warranted for any concrete code and dependency versions used later.

Recommendations

If you build an actual MCP server from this, separately audit the tools, resources, and HTTP endpoints you add, because the main risk comes from the later implementation rather than this document itself.
Pin and review dependency versions such as `@modelcontextprotocol/sdk` and `zod`, preferably with reproducible installs and integrity checks.
Confirm the repository license and recent maintenance status before reusing its patterns or code in production.
If you later enable remote HTTP transport, additionally assess data egress scope, authentication, and log redaction practices.

Audited by: gpt-5.4 · 2026-06-17

// install

Copy the install command and let the AI configure it · recommended for beginners

Please install the "mcp-server-patterns" skill from askskill:
1. Download https://raw.githubusercontent.com/affaan-m/ECC/main/skills/mcp-server-patterns/SKILL.md
2. Save it as ~/.claude/skills/mcp-server-patterns/SKILL.md
3. Reload skills and tell me it's ready

// download

Download SKILL.mdInstall manifest ↗

// examples

Create a basic MCP server

Prompt

Using the Node.js and TypeScript SDK, create a minimal runnable MCP server example with one tool, one resource, and one prompt, using Zod for parameter validation. Include the project structure, key code, and startup commands.

Expected

A runnable MCP server starter example with folder structure, TypeScript code, and run instructions.

Design tools and parameter validation

Prompt

I want to add two tools to an MCP server: web page summarization and keyword extraction. Using the TypeScript SDK, design the input and output schemas, validate parameters with Zod, and explain best practices for error handling and response formats.

Expected

Schema and implementation guidance for both tools, including Zod validation, error handling, and standardized response structures.

Compare stdio and HTTP transport

Prompt

Compare stdio and Streamable HTTP transport options for an MCP server. Explain use cases, deployment approaches, pros and cons, and provide configuration examples with the Node/TypeScript SDK.

Expected

A clear transport comparison with configuration examples to help choose the right MCP server integration approach.

// docs

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.

For the broader routing decision of when a capability should be a rule, a skill, MCP, or a plain CLI/API workflow, see docs/capability-surface-selection.md.

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.