mcp-builder

Design and maintain MCP servers for Python and Node/TypeScript.

1|Updated Sep 24, 2025
One-click install
npx skills add https://github.com/YavlPro/YavlGold --skill mcp-builder-yavlpro
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: mcp-builder
Source: https://github.com/YavlPro/YavlGold/tree/main/.kilocode/skills/mcp-builder
Command: npx skills add https://github.com/YavlPro/YavlGold --skill mcp-builder-yavlpro

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Build and maintain robust MCP servers that expose safe, well-documented tools to AI agents for external API interactions.

Core Features & Use Cases

  • Guidance for designing MCP servers that support both Python (FastMCP) and Node/TypeScript (MCP SDK)
  • Best practices for tool discovery, input validation, error handling, pagination, and security
  • Real-world examples and implementation patterns to accelerate development

Quick Start

Create a new MCP server named my_service_mcp and register a tool to expose an external API.

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 Python or TypeScript to expose external APIs to AI agents?

Build MCP servers using Python with FastMCP or Node with the MCP SDK to expose safe, well-documented tools for AI agent API interactions. The approach covers tool discovery, input validation, error handling, and pagination across both implementations.

What is the best way to handle tool discovery and input validation when designing an MCP server?

Tool discovery and input validation for MCP servers are managed through a frontmatter-driven model and rigorous tool annotation. This enforces strict validation and documentation requirements to ensure robust, safe tooling for scalable AI workflows.

Can I use FastMCP and the MCP SDK to implement pagination and security best practices for AI agents?

Yes, FastMCP and the MCP SDK support implementing pagination, error handling, and security best practices. These frameworks provide real-world implementation patterns to safely manage external API interactions for AI workflows.

Do I need a specific directory structure for scripts and reference assets when creating an MCP server?

MCP server creation uses an optional resource directory structure for scripts, references, and assets. Combined with frontmatter-driven discovery, this structure enforces rigorous tool annotation and documentation requirements for safe tooling.

What security practices should I follow when exposing external API tools to AI agents via an MCP server?

Security practices for MCP servers include rigorous tool annotation, input validation, and strict error handling. Applying these across Python and TypeScript implementations ensures safe, well-documented tools for scalable AI workflows interacting with external APIs.