Mcp Builder

composiohq/awesome-claude-skillsOfficial

If you're building an MCP server to connect external APIs to LLMs, this is a systematic guide that walks you through the full process. It starts with research principles like designing for workflows instead of just wrapping endpoints, then moves through studying the MCP protocol docs and your target API, and finally into implementation with language-specific guidance for Python (FastMCP) and TypeScript. The philosophy is evaluation-driven development: prototype fast, test with real agent interactions, and iterate based on how well the LLM actually accomplishes tasks. It's thorough on the details that matter, like designing error messages that guide the agent toward corrections and managing context limits with concise response formats.

skills.sh installs: 4.7K
GitHub stars: 79.2K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add composiohq/awesome-claude-skills --skill mcp-builder --agent claude-code

Installs into .claude/skills of the current project.

Files

MCP Server Development Guide

Overview

To create high-quality MCP (Model Context Protocol) servers that enable LLMs to effectively interact with external services, use this skill. An MCP server provides tools that allow LLMs to access external services and APIs. The quality of an MCP server is measured by how well it enables LLMs to accomplish real-world tasks using the tools provided.

Process

🚀 High-Level Workflow

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

Phase 1: Deep Research and Planning

1.1 Understand Agent-Centric Design Principles

Before diving into implementation, understand how to design tools for AI agents by reviewing these principles:

Build for Workflows, Not Just API Endpoints:

Don't simply wrap existing API endpoints - build thoughtful, high-impact workflow tools
Consolidate related operations (e.g., schedule_event that both checks availability and creates event)
Focus on tools that enable complete tasks, not just individual API calls
Consider what workflows agents actually need to accomplish

SKILL.md on GitHub