What problem does it solve? Building Model Context Protocol servers that LLMs can actually use effectively requires deep knowledge of the MCP specification, SDK patterns, tool design, and evaluation—this Skill provides a structured four-phase workflow covering research, implementation, review, and evaluation. ## Core Features & Use Cases - End-to-End MCP Development Workflow: Walks through research and planning, implementation, code review, and evaluation phases for building MCP servers in Python (FastMCP) or TypeScript (MCP SDK). - Language-Specific Reference Guides: Includes detailed implementation guides for TypeScript (Zod schemas, registerTool patterns, transports) and Python, plus MCP best practices covering naming, pagination, security, and error handling. - Evaluation Harness: Ships Python scripts to create XML-based evaluation question sets and run them against MCP servers over stdio, SSE, or streamable HTTP, producing accuracy reports with per-task tool-call metrics. - Use Case: You need to expose a company's internal API to Claude. Use this Skill to design well-named tools with proper schemas and annotations, implement the server, then generate 10 complex read-only evaluation questions and measure how accurately an LLM answers them using only your tools. ## Quick Start Help me build an MCP server for the GitHub API in TypeScript following the mcp-builder workflow, then create and run an evaluation for it.
