mcp-builder

Create TypeScript or Python MCP servers for external API integrations.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/MoonBoi9001/claude-code-cli-tools --skill mcp-builder-moonboi9001
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: mcp-builder
Source: https://github.com/MoonBoi9001/claude-code-cli-tools/tree/main/skills/mcp-builder
Command: npx skills add https://github.com/MoonBoi9001/claude-code-cli-tools --skill mcp-builder-moonboi9001

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Enable teams to design and implement MCP (Model Context Protocol) servers that let large language models reliably call external APIs and tools, reducing integration friction and improving agent effectiveness.

Core Features & Use Cases

  • Design guidance and conventions: Clear tool naming, discoverability, and context management best practices to help agents find and use tools reliably.
  • Language-specific implementation patterns: TypeScript (Zod + MCP SDK + streamable HTTP) and Python (FastMCP + Pydantic + stdio) guides with input/output schema recommendations.
  • Testing and evaluation: Built-in evaluation harness, QA guidelines, and example evaluation files to verify agent workflows and stability before deployment.
  • Use Case: Build a GitHub or Slack integration MCP server that exposes well-named, paginated read-only tools and structured outputs so an LLM can complete complex multi-step queries.

Quick Start

Scaffold a TypeScript or Python MCP server using the included language guides, register tools with Zod or Pydantic schemas, and run the provided evaluation harness to validate agent behavior.

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 for external API integrations?

To build an MCP server for external API integrations, you scaffold a TypeScript or Python project, register tools using Zod or Pydantic schemas, and configure streamable HTTP or stdio transport for LLM interaction.

What is the Model Context Protocol used for in LLM workflows?

The Model Context Protocol is used to let large language models reliably call external APIs and workflow tools, reducing integration friction and improving agent effectiveness during complex multi-step queries.

Does MCP server development support both TypeScript and Python?

MCP server development supports TypeScript using the MCP SDK with streamable HTTP and Zod schemas, and Python using FastMCP with stdio transport and Pydantic schemas for tool registration.

How do I test and evaluate LLM agent workflows with an MCP server?

You test and evaluate LLM agent workflows with an MCP server by running the provided evaluation harness, applying QA guidelines, and verifying agent behavior and stability before deployment.

What's the best way to structure tool schemas and pagination in MCP?

The best way to structure tool schemas and pagination in MCP is to use clear tool naming, define input/output schemas with Zod or Pydantic, include pagination metadata, and return structuredContent responses.

When should I use stdio vs streamable HTTP transport for MCP servers?

Use stdio transport for Python FastMCP integrations and streamable HTTP for TypeScript MCP SDK servers, selecting based on your language environment and workflow transport requirements.