What problem does it solve? Building MCP (Model Context Protocol) servers that LLMs can actually use effectively requires careful tool design, schema validation, transport configuration, and evaluation—this Skill provides a structured four-phase process covering all of it. ## Core Features & Use Cases - End-to-End MCP Server Workflow: Covers research and planning, implementation, review and testing, and evaluation creation for both TypeScript (MCP SDK) and Python (FastMCP) servers. - Reference Guides: Includes best practices for tool naming, pagination, transport selection (Streamable HTTP vs stdio), security (OAuth 2.1, input validation, rate limiting), and language-specific implementation patterns with Zod and Pydantic. - Evaluation Harness: Ships Python scripts to run XML-based QA evaluations against your MCP server via stdio, SSE, or HTTP transports, producing accuracy reports with per-task tool-call metrics. - Use Case: You want to expose the GitHub API to an LLM agent. Follow the guide to design tools like github_create_issue, implement them with Zod schemas and annotations, test with MCP Inspector, then generate 10 complex read-only evaluation questions and run the harness to measure agent accuracy. ## Quick Start Ask the assistant to help you build an MCP server for your chosen API, specifying whether you want TypeScript or Python and which transport to use.
