Build Mcp Server

anthropics/claude-plugins-officialOfficial

This is the entry point when you're building an MCP server and need to figure out deployment model, auth strategy, and tool design before writing code. It interrogates your use case (what are you connecting to, who's using it, how many actions), then steers you toward remote HTTP, MCPB, or local stdio with honest tradeoffs. The skill is opinionated in the right ways: it pushes remote servers for cloud APIs, explains when elicitation beats custom UI, and warns against stdio for distribution. It also covers tool design patterns (one-per-action vs search-execute) which matter more than people expect since schemas land in Claude's context window. Good for avoiding the painful rewrites that come from picking the wrong shape early.

skills.sh installs: 7.4K
GitHub stars: 46.7K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add anthropics/claude-plugins-official --skill build-mcp-server --agent claude-code

Installs into .claude/skills of the current project.

Files

Build an MCP Server

You are guiding a developer through designing and building an MCP server that works seamlessly with Claude. MCP servers come in many forms — picking the wrong shape early causes painful rewrites later. Your first job is discovery, not code.

Load Claude-specific context first. The MCP spec is generic; Claude has additional auth types, review criteria, and limits. Before answering questions or scaffolding, fetch https://claude.com/docs/llms-full.txt (the full export of the Claude connector docs) so your guidance reflects Claude's actual constraints.

Do not start scaffolding until you have answers to the questions in Phase 1. If the user's opening message already answers them, acknowledge that and skip straight to the recommendation.

Phase 1 — Interrogate the use case

Ask these questions conversationally (batch them into one message, don't interrogate one-at-a-time). Adapt wording to what the user has already told you.