This walks you through building MCP servers that let LLMs interact with external APIs. It covers the full cycle: researching the MCP spec and target API, implementing tools with proper schemas and error handling, testing with the MCP Inspector, and creating evaluation questions to verify your server actually works. The guide pushes you toward TypeScript with streamable HTTP for remote servers, emphasizes comprehensive API coverage over workflow shortcuts, and includes concrete advice on tool naming and response formatting. The evaluation phase is thorough, requiring 10 complex read-only questions with verifiable answers. If you're shipping an MCP server and want a structured process instead of guessing at best practices, this gives you a clear roadmap.

skills.sh installs
690
GitHub stars
43.1K
last updated
Jul 14, 2026

Install

$ npx -y skills add sickn33/antigravity-awesome-skills --skill mcp-builder --agent claude-code

Installs into .claude/skills of the current project.

Files

MCP Server Development Guide

Modified in AAS on 2026-09-05: version-scoped examples and bounded evaluation.

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. Start with the minimum operations needed for the user's authorized workflow. Expand coverage from observed gaps.

Sponsors

Details

Repository
github.com/sickn33/antigravity-awesome-skills
Category
AI & Agent Building
First seen
May 16, 2026

More from sickn33/antigravity-awesome-skills

All 708
1aradotso avatarzen-ai-pentest-frameworkaradotso/security-skillszen ai pentest framework676skills.sh installs
2alchaincyf avatarhuashu-agent-swarmalchaincyf/huashu-skills多Agent蜂群并行协作,纯git自组织,适合大型项目开发。当用户提到"蜂群模式"、"多agent"、"并行开发"、"agent swarm"时使用。672skills.sh installs
3breath57 avatardingtalk-ai-tablebreath57/dingtalk-skills钉钉 AI 表格(多维表格)操作。当用户提到"钉钉AI表格"、"AI表格"、"多维表格"、"工作表"、"字段"、"记录"、"新增记录"、"查询记录"、"更新记录"、"删除记录"、"新建字段"、"删除字段"、"dingtalk AI table"、"dingtalk notable"、"able文件"时使用此技能。支持工668skills.sh installs
4alirezarezvani avatarmcp-server-builderalirezarezvani/claude-skillsDesign and ship production-ready MCP (Model Context Protocol) servers from OpenAPI contracts instead of hand-written tool wrappers. Python and TypeScript suppor663skills.sh installs
5alchaincyf avatarhuashu-prompt-savealchaincyf/huashu-skills自动识别Prompt类型并分类保存(技术/内容/教学/产品/通用)。当用户提到"保存prompt"、"记录prompt"、"整理prompt"时使用。662skills.sh installs
6qodex-ai avatarecommerce-platform-specialistqodex-ai/ai-agent-skillsProvide expert guidance on Shopify e-commerce platform. Advises on store setup, products, customization, and optimization.657skills.sh installs