🔌

AI EngineeringPython

MCP Builder

MCP Builder is an AI Engineering skill for Claude Code, published by anthropics in skills.

168.6K stars20.1K forkson anthropics/skillsAdded 2026/08/13Repository updated 2026/08/07

View source on GitHub Download repo ZIP

agent-skills

Install in seconds

Install MCP Builder

Copy MCP Builder into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/anthropics/skills/tree/main/skills/mcp-builder ~/.claude/skills/mcp-builder

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/anthropics/skills.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: skills/mcp-builder/SKILL.md in anthropics/skills
Installs to: ~/.claude/skills/mcp-builder
Collection: One of 18 skills cataloged from this repository
Category: AI Engineering — 2451 skills

What MCP Builder does

MCP Builder provides a workflow for creating MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. It covers research, implementation, testing, and evaluation when building MCP servers in Python (FastMCP) or Node/TypeScript (MCP SDK).

MCP Builder is cataloged under AI Engineering on DirSkills. MCP Builder comes from a repository tagged agent-skills.

Documentation

README

Excerpt

MCP Server Development Guide

Overview

Create MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. The quality of an MCP server is measured by how well it enables LLMs to accomplish real-world tasks.

Process

🚀 High-Level Workflow

Creating a high-quality MCP server involves four main phases:

Phase 1: Deep Research and Planning

1.1 Understand Modern MCP Design

This is the opening of the README. Read the full README on GitHub.

Frequently asked about MCP Builder

What else does anthropics publish alongside MCP Builder?
MCP Builder is one of 18 skills that DirSkills catalogs from anthropics/skills, the repository it ships in. Its siblings there include Algorithmic Art, Brand Guidelines and Canvas Design. Each one is a separate skill with its own page in this directory, installs the same way MCP Builder does, and is maintained by anthropics in that same repository. The rest of the collection is listed on the anthropics/skills page.
How does MCP Builder compare to other AI Engineering skills?
MCP Builder ranks #21 by stars among the 2451 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of MCP Builder against them. Open each page to compare what they document and how they install.

More from anthropics/skills

MCP Builder is one of 18 skills cataloged on DirSkills from anthropics/skills.

See all 18 skills →

Algorithmic Art

Algorithmic Art creates original generative art using p5.js with seeded randomness and interactive parameter exploration. Use it when users request code-based art, flow fields, particle systems, or other algorithmic visualizations.

Brand Guidelines

Brand Guidelines applies Anthropic's official brand colors and typography to artifacts that benefit from the company's look-and-feel. Use it when brand colors, style guidelines, visual formatting, or company design standards apply.

Canvas Design

Canvas Design creates original visual art in .png and .pdf documents guided by design philosophy. Use it when asked to create posters, art pieces, or other static designs, never copying existing artists' work to avoid copyright violations.

Claude API

Claude API provides reference documentation for the Anthropic SDK, covering model IDs, pricing, parameters, streaming, tool use, MCP, agents, caching, token counting, and model migration. Use it before writing Claude integration code or when asked about Claude/Anthropic APIs, models, or limits.

Doc Co-Authoring

Doc Co-Authoring guides users through a structured workflow for co-authoring documentation, from context gathering and iterative refinement to reader testing. Use it when writing proposals, technical specs, decision docs, or similar structured content.

Frontend Design

Frontend Design guides distinctive, intentional visual design for building new UI or reshaping existing ones, including aesthetic direction, typography, and avoiding templated defaults. Use it when you need deliberate, non-generic visual choices for a frontend.

More AI Engineering skills

MCP Builder is one of 2451 AI Engineering skills cataloged on DirSkills, ranked #21 by stars among them.

Browse all AI Engineering skills →

Architecture Decision Records

Architecture Decision Records captures architectural decisions made during Claude Code sessions as structured ADRs, recording context, alternatives, and rationale. Use it when significant technical choices are made so future developers understand why the codebase is shaped the way it is.

AI-First Engineering

AI-First Engineering defines process, review, and architecture standards for teams where AI agents produce most implementation output. Use it to set ownership rules, quality gates, and evaluation criteria for agent-generated code.

Agentic OS

Agentic OS codifies a persistent multi-agent operating system architecture for Claude Code. Use it when building a multi-agent workflow with file-based memory, slash commands, and scheduled automation that survives session restarts.