mcp-builder

Build MCP servers with FastMCP or MCP SDK for LLM tasks.

1|1|Updated Dec 21, 2025
One-click install
npx skills add https://github.com/Kjdragan/universal_agent --skill mcp-builder-kjdragan
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: mcp-builder
Source: https://github.com/Kjdragan/universal_agent/tree/main/.claude/skills/mcp-builder
Command: npx skills add https://github.com/Kjdragan/universal_agent --skill mcp-builder-kjdragan

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires anthropic, mcp.

What problem does it solve?

This Skill provides a comprehensive, code-first guide for building MCP servers that expose tools, resources, and prompts for LLMs, enabling seamless integration with external services.

Core Features & Use Cases

  • Guided MCP server scaffolding for Python (FastMCP) and Node/TypeScript (MCP SDK) implementations.
  • Tool design and registration best practices: naming conventions, input validation (Pydantic/Zod), and secure error handling.
  • SDK-driven implementation patterns: examples of stdio and streamable HTTP transports, resources, and advanced features.

Quick Start

Install dependencies (anthropic, mcp) and follow the examples to bootstrap a new MCP server for your service.

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 with Python or TypeScript?

You scaffold an MCP server using Python FastMCP or Node/TypeScript MCP SDK, then register tools, resources, and prompts with typed input validation and secure error handling for LLM orchestration.

What is the best way to validate tool inputs when building MCP servers?

The best way to validate tool inputs for MCP servers is enforcing strict schema validation using Pydantic for Python FastMCP or Zod for Node/TypeScript MCP SDK implementations.

Does the MCP SDK support both stdio and streamable HTTP transports?

Yes, the MCP SDK supports both stdio and streamable HTTP transports, providing implementation patterns to orchestrate tools, resources, and prompts for various LLM-driven tasks.

How do I handle errors and pagination in MCP tool registration?

Handle errors and pagination in MCP tool registration by applying secure error handling best practices and implementing pagination logic to manage large datasets exposed to LLMs.

What security best practices should I apply when exposing tools to LLMs?

Security best practices for exposing tools to LLMs include enforcing strict input validation, using typed tool interfaces, and applying proper secure error handling to prevent vulnerabilities in MCP server implementations.