Architectural guide and best practices for building robust Model Context Protocol servers.

Install

mkdir -p .claude/skills/mcp-builder-underundregh && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/12090" && unzip -o skill.zip -d .claude/skills/mcp-builder-underundregh && rm skill.zip

Installs to .claude/skills/mcp-builder-underundregh

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

MCP (Model Context Protocol) server building principles. Tool design, resource patterns, best practices.
104 charsno explicit “when” trigger
Advanced

Key capabilities

  • Define tools as functions AI can call.
  • Implement resources as data AI can read.
  • Structure prompts using pre-defined templates.
  • Design tools with clear names, single purpose, validated input, and structured output.
  • Handle errors by returning structured messages without exposing internal details.

How it works

The skill outlines principles for building MCP servers, focusing on tool design, resource patterns, error handling, and security to create validated, schema-driven components.

Inputs & outputs

You give it
Requirements for an MCP server, tools, or resources
You get back
MCP server components designed according to principles, including tools, resources, and error handling

When to use mcp-builder

  • Design custom MCP tools
  • Structure resources for AI access
  • Implement server architecture

About this skill

MCP Builder

ultrathink

"Сисадмин но дзюцу!!!" — When the MCP server magically works on first try. "Человечек сориентирует." — MCP tools are sub-routines you wire up for the model.

Principles for building MCP servers.


1. MCP Overview

What is MCP?

Model Context Protocol - standard for connecting AI systems with external tools and data sources.

Core Concepts

ConceptPurpose
ToolsFunctions AI can call
ResourcesData AI can read
PromptsPre-defined prompt templates

2. Server Architecture

Project Structure

my-mcp-server/
├── src/
│   └── index.ts      # Main entry
├── package.json
└── tsconfig.json

Transport Types

TypeUse
StdioLocal, CLI-based
SSEWeb-based, streaming
WebSocketReal-time, bidirectional

3. Tool Design Principles

Good Tool Design

PrincipleDescription
Clear nameAction-oriented (get_weather, create_user)
Single purposeOne thing well
Validated inputSchema with types and descriptions
Structured outputPredictable response format

Input Schema Design

FieldRequired?
TypeYes - object
PropertiesDefine each param
RequiredList mandatory params
DescriptionHuman-readable

4. Resource Patterns

Resource Types

TypeUse
StaticFixed data (config, docs)
DynamicGenerated on request
TemplateURI with parameters

URI Patterns

PatternExample
Fixeddocs://readme
Parameterizedusers://{userId}
Collectionfiles://project/*

5. Error Handling

Error Types

SituationResponse
Invalid paramsValidation error message
Not foundClear "not found"
Server errorGeneric error, log details

Best Practices

  • Return structured errors
  • Don't expose internal details
  • Log for debugging
  • Provide actionable messages

6. Multimodal Handling

Supported Types

TypeEncoding
TextPlain text
ImagesBase64 + MIME type
FilesBase64 + MIME type

7. Security Principles

Input Validation

  • Validate all tool inputs
  • Sanitize user-provided data
  • Limit resource access

API Keys

  • Use environment variables
  • Don't log secrets
  • Validate permissions

8. Configuration

Claude Desktop Config

FieldPurpose
commandExecutable to run
argsCommand arguments
envEnvironment variables

9. Testing

Test Categories

TypeFocus
UnitTool logic
IntegrationFull server
ContractSchema validation

10. Best Practices Checklist

  • Clear, action-oriented tool names
  • Complete input schemas with descriptions
  • Structured JSON output
  • Error handling for all cases
  • Input validation
  • Environment-based configuration
  • Logging for debugging

Remember: MCP tools should be simple, focused, and well-documented. The AI relies on descriptions to use them correctly.

When not to use it

  • When building a server that does not adhere to the Model Context Protocol (MCP).
  • When the user wants to expose internal server details in error messages.
  • When the user does not want to validate tool inputs.

Limitations

  • Focuses on Model Context Protocol (MCP) principles.
  • Requires input validation for all tool inputs.
  • Does not expose internal details in error responses.

How it compares

This skill provides a standardized framework for building AI-connected tools and data sources, ensuring consistency and predictability, unlike ad-hoc server development.

Compared to similar skills

mcp-builder side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
mcp-builder (this skill)02moNo flagsAdvanced
mcp-builder1363moReviewAdvanced
copilot-sdk74moReviewIntermediate
chatgpt-app-builder52moReviewAdvanced

Try saying

Example prompts that trigger this skill in your AI assistant.

You might also like

mcp-builder

anthropics

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

136215

copilot-sdk

github

Build agentic applications with GitHub Copilot SDK. Use when embedding AI agents in apps, creating custom tools, implementing streaming responses, managing sessions, connecting to MCP servers, or creating custom agents. Triggers on Copilot SDK, GitHub SDK, agentic app, embed Copilot, programmable agent, MCP server, custom agent.

763

chatgpt-app-builder

mcp-use

Build ChatGPT apps with interactive widgets using mcp-use and OpenAI Apps SDK. Use when creating ChatGPT apps, building MCP servers with widgets, defining React widgets, working with Apps SDK, or when user mentions ChatGPT widgets, mcp-use widgets, or Apps SDK development.

535

create-mcp-app

modelcontextprotocol

This skill should be used when the user asks to "create an MCP App", "add a UI to an MCP tool", "build an interactive MCP View", "scaffold an MCP App", or needs guidance on MCP Apps SDK patterns, UI-resource registration, MCP App lifecycle, or host integration. Provides comprehensive guidance for building MCP Apps with interactive UIs.

331

retellai-hello-world

jeremylongshore

Create a minimal working Retell AI example. Use when starting a new Retell AI integration, testing your setup, or learning basic Retell AI API patterns. Trigger with phrases like "retellai hello world", "retellai example", "retellai quick start", "simple retellai code".

31

m365-agents-ts

T-Sunm

Microsoft 365 Agents SDK for TypeScript/Node.js.

00

Search skills

Search the agent skills registry