mcp-server-patterns
affaan-m/everything-claude-code
Build MCP servers with Node/TypeScript SDK—tools, resources, prompts, Zod validation, stdio vs HTTP transport.
What is mcp-server-patterns?
Build Model Context Protocol servers that expose tools, resources, and prompts to AI assistants. Use this skill when implementing new MCP servers, adding capabilities, choosing transport (stdio for local, Streamable HTTP for remote), or upgrading the SDK.
- Register tools (callable actions) with input schemas and handlers
- Register resources (read-only data) accessible via URI
- Register prompts (reusable parameterized templates)
- Choose between stdio transport (local clients like Claude Desktop) and Streamable HTTP (remote clients like Cursor)
- Validate inputs with Zod schemas
- Structure error responses for model interpretation
How to install mcp-server-patterns
npx skills add https://github.com/affaan-m/everything-claude-code --skill mcp-server-patterns- Node.js and npm
- @modelcontextprotocol/sdk package
- Zod or equivalent schema validation library
- Familiarity with TypeScript (recommended)
How to use mcp-server-patterns
- 1.Install @modelcontextprotocol/sdk and zod: npm install @modelcontextprotocol/sdk zod
- 2.Create a McpServer instance with name and version
- 3.Define Zod schemas for tool and resource inputs
- 4.Register tools using the current SDK API (tool() or registerTool() depending on version)
- 5.Register resources with URI handlers
- 6.Register prompts if needed
- 7.Choose transport: stdio for local (Claude Desktop) or Streamable HTTP for remote (Cursor, cloud)
- 8.Connect the server using the appropriate transport factory or constructor
Use cases
- Building a new MCP server to expose custom tools to Claude or Cursor
- Adding tools or resources to an existing MCP server
- Migrating from stdio to Streamable HTTP for remote client support
- Upgrading the Node/TypeScript SDK and updating registration patterns
- Debugging MCP registration, transport, or handler issues
- Backend developers building AI-integrated services
- MCP server maintainers
- Teams integrating Claude or Cursor with custom APIs or workflows
mcp-server-patterns FAQ
The Node/TypeScript SDK API has evolved. Check the official MCP documentation at modelcontextprotocol.io or query Context7 for "MCP" to find the current method signatures for your installed version. Always verify before copying examples.
Use stdio for local clients like Claude Desktop. Use Streamable HTTP for remote clients (Cursor, cloud deployments). Keep server logic independent of transport so you can switch in the entrypoint.
Return structured errors or messages the model can interpret. Avoid raw stack traces. Document expected error cases in the tool description.
Prefer idempotent tools where possible so retries are safe. If a tool has side effects, document the behavior clearly.
Pin the SDK version in package.json, check release notes for API changes, and verify registration patterns against the current official MCP documentation.
Full instructions (SKILL.md)
Source of truth, from affaan-m/everything-claude-code.
name: mcp-server-patterns description: Build MCP servers with Node/TypeScript SDK — tools, resources, prompts, Zod validation, stdio vs Streamable HTTP. Use Context7 or official MCP docs for latest API. metadata: origin: ECC
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()ortool()depending on SDK version. - Resources: Read-only data the model can fetch (e.g. file contents, API responses). Register with
registerResource()orresource(). Handlers typically receive auriargument. - 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.
Related skills
More from affaan-m/everything-claude-code and the wider catalog.
security-review
Security checklist and patterns for authentication, input validation, secrets, and sensitive features.
golang-patterns
Idiomatic Go patterns, best practices, and conventions for building robust, efficient, and maintainable applications.
coding-standards
Baseline coding conventions for naming, readability, immutability, and quality across projects.
frontend-patterns
React and Next.js patterns for components, state management, performance, and modern frontend practices.
backend-patterns
REST/GraphQL API design, database optimization, and server-side patterns for Node.js, Express, and Next.js.
golang-testing
Go testing patterns: table-driven tests, subtests, benchmarks, fuzzing, and TDD methodology.