skills.rest
Clay-HHK
Clay-HHKCOMMUNITY
Explore all skills by this author →
GitHub

mcp-builder

Build MCP servers in Python or TypeScript with schemas, transports, and evaluation.

2|Updated Apr 12, 2026
Search Tags:#typescript#evaluation#mcp#tool-design#fastmcp#mcp-server#streamable-http
One-click install
npx skills add https://github.com/Clay-HHK/claude-config --skill mcp-builder-clay-hhk
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: mcp-builder
Source: https://github.com/Clay-HHK/claude-config/tree/main/skills/mcp-builder
Command: npx skills add https://github.com/Clay-HHK/claude-config --skill mcp-builder-clay-hhk

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Provide developers a complete, opinionated workflow for designing, implementing, testing, and evaluating MCP (Model Context Protocol) servers so LLMs can reliably call external APIs and services through well-structured tools and transports.

Core Features & Use Cases

  • End-to-end guidance: Planning, tool selection, implementation patterns, and evaluation phases for Python (FastMCP) and TypeScript (MCP SDK).
  • Tool and schema design: Naming conventions, input/output schemas (Pydantic/Zod), structuredContent, and annotations to make tools discoverable and safe for agents.
  • Transport & response patterns: Recommendations for stdio and streamable HTTP transports, pagination, error handling, and response formats (JSON/Markdown).
  • Testing and evaluation: Built-in evaluation harness, example evaluation formats, and guidance for writing stable, verifiable QA tasks to measure server quality.
  • Utility scripts: Connection helpers and evaluation runner to list tools, call tools, and automate evaluation runs.

Quick Start

Follow the TypeScript or Python implementation guide to scaffold an MCP server, register clear, schema-validated tools, and run the provided evaluation harness to verify agent workflows.

Frequently Asked Questions about mcp-builder

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

FAQPage Schema
How do I build a production-ready MCP server for LLM agents?▼

You can build an MCP server using Python (FastMCP) or TypeScript (MCP SDK) by applying this Skill's patterns for schema-validated tools, pagination, authentication, and structured outputs to ensure reliable agent workflows.

What is the best way to design tool schemas for an MCP server?▼

Design MCP tool schemas by following naming conventions and using Pydantic or Zod for input/output validation, adding annotations and structuredContent to make tools discoverable and safe for LLM agents.

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

Select stdio or streamable HTTP transport based on your deployment context; this Skill provides recommendations for both, including response patterns like JSON or Markdown and proper error handling for external API exposure.

How do I test and evaluate MCP server tool calls?▼

Test and evaluate MCP servers using the built-in evaluation harness and utility scripts to list tools, call tools, and run automated, verifiable QA tasks that measure server quality during agent workflows.

Can I use FastMCP to expose external APIs with pagination to LLMs?▼

Yes, you can use FastMCP to expose external APIs to LLMs by implementing the Skill's pagination, authentication, and error handling patterns to manage large or structured API responses effectively.

Does the MCP SDK support structured tool outputs for TypeScript agents?▼

Yes, the MCP SDK supports TypeScript agents by utilizing Zod schemas for input/output validation and structuredContent, ensuring tools return structured data that agents can reliably parse and use.

Related Skills

Explore More Software Engineering Skills→
robertbr123robertbr123

fastmcp

Automate creation, testing, and deployment of MCP servers in Python using FastMCP.

Community
Intermediate
tylerjrbuelltylerjrbuell
21

mcp-tool-integration

Connect Reactive Agents to MCP servers with automatic transport detection and Docker lifecycle management.

Community
Advanced
ovachieverovachiever
52

instructor

Extract structured data from LLM responses with Pydantic validation and retries.

Community
Advanced
pkoka888pkoka888
1

mcp-builder

Build MCP servers exposing validated, agent-friendly tools for external APIs.

Community
Advanced