← ClaudeAtlas

mcp-builderlisted

Build high-quality MCP servers with strong tool design, structured outputs, clear error handling, and realistic evaluations. Use when creating or improving MCP servers in TypeScript or Python for external APIs, services, or internal platforms.
bg-szy/TOP-SKILLS · ★ 1 · AI & Automation · score 70
Install: claude install-skill bg-szy/TOP-SKILLS
# MCP Builder Design MCP servers that are easy for agents to discover, compose, and trust. - Leverage native parallel subagent dispatch and 200k+ context windows where available. ## When to Use Use symptom -> action triggers: when one matches, apply this skill and verify with the protocol below. - You are creating a new MCP server around an external API or internal platform. - An existing MCP server needs better tool naming, schemas, pagination, or error handling. - You need a workflow for evaluating whether an MCP server is actually useful for real agent tasks. - You are deciding between TypeScript and Python MCP implementations. ## Glossary - MCP Inspector: An interactive client for browsing registered tools, schemas, inputs, and outputs while you validate a server. - Structured outputs: Predictable JSON or schema-backed payloads that downstream agents can parse safely instead of scraping prose. - Workflow tool: A higher-level tool that coordinates several lower-level API steps into one agent-friendly operation. ## Core Workflow ### 1. Research First Before implementation: 1. Read the current MCP protocol documentation. 2. Read the relevant SDK guide for your implementation language. 3. Review the target service API and list the highest-value operations. 4. Decide which operations should stay low-level and which deserve dedicated workflow tools. ### 2. Design Agent-Friendly Tools Prefer tools that are easy to discover and compose: - use clear action-oriented