oberconcejo/VS-CODE / .agents/skills/mcp-server-patterns
mcp-server-patterns
VerifiedBuild MCP servers with Node/TypeScript SDK — tools, resources, prompts, Zod validation, stdio vs Streamable HTTP. Use Context7 or official MCP docs for latest API. Use when building or debugging an MCP server — tools, resources, prompts, validation, or transport choice.
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
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-changelog-updatemorluto/reaPrepare or rewrite REA release changelogs and GitHub release notes from pinned Git history, with verified contributor thanks and Release Please synchronization. | Stars: 466k | Updated | Claude CodeCodex | Verified | Install |
| academy-guideanthropics/skillsStop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |
| claude-apianthropics/skillsReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file). | Stars: 196k | Updated | Claude CodeCodex | Unverified | Install |
| doc-coauthoringanthropics/skillsGuide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |