What problem does it solve? Building MCP (Model Context Protocol) servers that LLMs can actually use effectively requires careful tool design, schema validation, transport selection, and evaluation—this Skill provides a structured four-phase process to do it right. ## Core Features & Use Cases - Four-Phase Workflow: Deep research and planning, implementation, review and testing, and evaluation creation for MCP servers. - Language-Specific Guides: Reference documentation for Python (FastMCP) and Node/TypeScript (MCP SDK) with naming conventions, Zod/Pydantic schemas, pagination, and error handling patterns. - Evaluation Harness: Scripts to run XML-based QA evaluations against your MCP server over stdio, SSE, or streamable HTTP transports, producing accuracy reports. - Use Case: You need to expose the GitHub API to an LLM agent. Follow the guide to design tools like github_create_issue, implement them with proper annotations and pagination, then generate 10 complex read-only evaluation questions and run the harness to measure agent accuracy. ## Quick Start Ask the agent to help you build an MCP server for your chosen API, specifying whether you want Python or TypeScript and which transport to use.
