mcp-builder

Create MCP servers with Python FastMCP or Node/TypeScript SDKs.

Updated Mar 6, 2026
One-click install
npx skills add https://github.com/pczhao1210/reuseable-agents-and-skills --skill mcp-builder-pczhao1210
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: mcp-builder
Source: https://github.com/pczhao1210/reuseable-agents-and-skills/tree/main/.agents/skills/mcp-builder
Command: npx skills add https://github.com/pczhao1210/reuseable-agents-and-skills --skill mcp-builder-pczhao1210

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Provide a complete development guide and checklist for building MCP (Model Context Protocol) servers so that LLM-based agents can reliably interact with external APIs and services through well-designed, discoverable tools.

Core Features & Use Cases

  • End-to-end design workflow: Research, plan, implement, test, and evaluate MCP servers across four phases to ensure production quality.
  • Language and transport guidance: Patterns and examples for Python (FastMCP) and Node/TypeScript (MCP SDK), with recommendations for stdio and streamable HTTP transports.
  • Tool design and validation: Tool naming conventions, input/output schema best practices (Pydantic/Zod), annotations, pagination, error handling, and structured outputs for agent consumption.
  • Testing and evaluation: An evaluation harness and guidelines to create stable, verifiable, read-only evaluation tasks and measure agent performance.

Quick Start

Generate a TypeScript MCP server scaffold that registers tools with Zod input schemas, returns structuredContent, and exposes a streamable HTTP transport.

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 LLM integrations?

To build an MCP server, you register tools with input and output schemas, configure transports like stdio or streamable HTTP, and implement error handling. This Skill provides an end-to-end workflow across research, planning, implementation, and evaluation phases for production quality.

Can I use FastMCP to create a Model Context Protocol server in Python?

Yes, FastMCP is supported for creating a Model Context Protocol server in Python. The Skill provides specific patterns and examples for Python implementations, including tool registration, Pydantic schema validation, and structured outputs for agent consumption.

What's the best way to validate tool schemas for an MCP server?

The best way to validate tool schemas for an MCP server is using Pydantic for Python and Zod for TypeScript. This Skill guides you through defining input and output schemas, applying naming conventions, and adding annotations to ensure tools are discoverable and reliable.

Does this MCP server workflow support TypeScript and Node?

Yes, this MCP server workflow fully supports TypeScript and Node implementations using the MCP SDK. You can generate a TypeScript scaffold that registers tools with Zod input schemas, returns structuredContent, and exposes a streamable HTTP transport.

How do I test and evaluate an MCP server?

You test and evaluate an MCP server using an evaluation harness to create stable, verifiable, read-only evaluation tasks. This Skill provides guidelines for measuring agent performance to ensure your tools interact reliably with external APIs and services.