mcp-builder

Guides building MCP servers in TypeScript or Python with evaluation harness.

Updated Jun 14, 2026
One-click install
npx skills add https://github.com/ironkid90-s/lucky5-v7 --skill mcp-builder-ironkid90-s
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: mcp-builder
Source: https://github.com/ironkid90-s/lucky5-v7/tree/main/.github/skills/mcp-builder
Command: npx skills add https://github.com/ironkid90-s/lucky5-v7 --skill mcp-builder-ironkid90-s

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires anthropic, mcp, and includes scripts (resource) and references (resource) components.

What problem does it solve? Building Model Context Protocol servers that LLMs can actually use effectively requires careful tool design, schema validation, transport selection, and testing, which developers often get wrong without structured guidance. ## Core Features & Use Cases - Four-Phase Development Workflow: Covers research and planning, implementation, review and testing, and evaluation creation for MCP servers. - Language-Specific Guides: Provides reference documentation for TypeScript (MCP SDK with Zod) and Python (FastMCP with Pydantic) implementations. - Evaluation Harness: Includes Python scripts to run XML-based QA evaluations against MCP servers over stdio, SSE, or streamable HTTP transports. - Use Case: A developer integrating the GitHub API into an LLM agent uses this Skill to scaffold a well-named, paginated, annotated MCP server and then verify it with 10 read-only evaluation questions. ## Quick Start Ask the AI to help you build an MCP server for your chosen API, specifying whether you want TypeScript or Python.

Frequently Asked Questions about mcp-builder

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I build an MCP server in TypeScript?

Use the MCP TypeScript SDK's McpServer class and registerTool method with Zod schemas for input validation. Provide title, description, inputSchema, and annotations for each tool, then connect via StdioServerTransport for local use or StreamableHTTPServerTransport for remote deployment.

How do I test an MCP server with evaluations?

Create an XML file with qa_pair elements containing questions and verifiable answers, then run the evaluation.py script with your transport type. For stdio servers the script launches the server automatically; for SSE or HTTP you must start the server first and pass its URL.

Should I use stdio or streamable HTTP for my MCP server?

Use stdio for local integrations and command-line tools with a single client, and streamable HTTP for remote servers serving multiple clients. SSE is deprecated in favor of streamable HTTP, and stdio servers must log to stderr rather than stdout.

What makes a good MCP tool name?

Use snake_case with a service prefix and action-oriented verbs, such as github_create_issue or slack_send_message. This prevents naming conflicts when multiple MCP servers are used together and helps agents discover the right tool quickly.

What are the requirements for MCP evaluation questions?

Questions must be independent, read-only, non-destructive, and complex enough to require multiple tool calls. Answers must be single verifiable values that remain stable over time and can be checked by direct string comparison.