What problem does it solve? Building an MCP server that LLMs can actually use effectively requires careful tool design, protocol knowledge, and testing—this Skill provides a structured four-phase process covering research, implementation, review, and evaluation. ## Core Features & Use Cases - Four-Phase Workflow: Deep research and planning, implementation, review and testing, and evaluation creation for MCP servers. - Language-Specific Guidance: Reference guides for TypeScript (MCP SDK with Zod schemas) and Python (FastMCP with Pydantic models), including project structure and quality checklists. - Evaluation Framework: Instructions for creating 10 complex, read-only, verifiable evaluation questions in XML format to test whether LLMs can use the server effectively. - Use Case: You need to expose a third-party API to an LLM agent. Follow the workflow to design well-named tools with actionable error messages, implement them with the TypeScript SDK, test with MCP Inspector, and generate an evaluation suite. ## Quick Start Use the mcp-builder skill to help me build an MCP server in TypeScript that wraps the GitHub API with tools for issues and repositories.