MCP Builder
This guide helps developers build MCP servers for integrating external APIs and services. The quality of an MCP server is measured by how well it enables LLMs to accomplish real-world tasks.
Install
/plugin marketplace add anthropics/skillsThen run /plugin to install the skill set that includes it. In Claude.ai and the Claude app, Anthropic skills are built in: turn them on in Settings → Capabilities.
npx skills add anthropics/skills --skill mcp-buildergit clone --depth 1 https://github.com/anthropics/skills.git /tmp/skills
mkdir -p ~/.claude/skills
cp -r /tmp/skills/skills/mcp-builder ~/.claude/skills/mcp-builderPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
What this skill does
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
Trigger phrases
Claude loads this skill automatically when you say things like:
How it works
- Deep Research and Planning: Study MCP protocol documentation and modern design patterns
- Implementation: Set up project structure, create core infrastructure (API client, error handling)
- Review and Test: Evaluate code quality, ensure type coverage, test using MCP Inspector
- Create Evaluations: Develop comprehensive tests with realistic questions
When to use it
- When building MCP servers for API integration
- When creating tools for LLM-external service interaction
- When integrating Claude with external services
Best practices
- Use TypeScript as the preferred language
- Create comprehensive evaluations with 10+ complex questions
- Eliminate duplication and ensure proper error handling
From the SKILL.md
# 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 **API Coverage vs. Workflow Tools:** Balance comprehensive API endpoint coverage with specialized workflow tools. Workflow tools can be more convenient for specific tasks, while comprehensive coverage gives agents flexibility to compose operations. Performance varies by client—some clients benefit from code execution that combines basic tools, while others work better with higher-level workflows. When uncertain, prioritize comprehensive API coverage. **Tool Naming and Discoverability:** Clear, descriptive tool names help agents find the right tools quickly. Use consistent prefixes (e.g., `github_create_issue`, `github_list_repos`) and action-oriented naming. **Context Management:** Agents benefit from concise tool descriptions and the ability to filter/paginate results. Design tools that return focused, relevant data. Some clients support code execution which can help agents filter and process data efficiently. **Actionable Error Messages:**
Details
- Skill name
mcp-builder- Repository
- anthropics/skills
- Path
skills/mcp-builder/SKILL.md
FAQ
What does the MCP Builder skill do?
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
How do I install the MCP Builder skill?
Claude Code plugin: /plugin marketplace add anthropics/skills. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Related skills
Algorithmic Art
anthropics/skills
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.
Brand Guidelines
anthropics/skills
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.
Canvas Design
anthropics/skills
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.
Brainstorming
obra/superpowers
Transforms rough ideas into fully-formed designs. Structure your brainstorming sessions and develop ideas systematically.
Dispatching Parallel Agents
obra/superpowers
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
Executing Plans
obra/superpowers
Use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available
Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.