skills.rest
bill80362
bill80362COMMUNITY
Explore all skills by this author →
GitHub

mcp-builder

Guides design, implementation, testing, and deployment of Model Context Protocol servers.

Updated Aug 14, 2026
Search Tags:#typescript#python#mcp#ai integration#model context protocol#server development#tool design
One-click install
npx skills add https://github.com/bill80362/laravel-thread-admin --skill mcp-builder-bill80362
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: mcp-builder
Source: https://github.com/bill80362/laravel-thread-admin/tree/main/.github/superpowers/mcp-builder
Command: npx skills add https://github.com/bill80362/laravel-thread-admin --skill mcp-builder-bill80362

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Building MCP servers that AI assistants can reliably call requires many non-obvious decisions: choosing between Tools, Resources, and Prompts, naming and describing tools so AI selects them correctly, handling errors without crashing, and debugging stdio-based communication. This Skill provides a systematic methodology covering the full lifecycle. ## Core Features & Use Cases - Protocol Design Guidance: Clear rules for choosing Tools vs Resources vs Prompts, plus naming, parameter schema, and description conventions that make AI call tools correctly. - Implementation Patterns: TypeScript and Python project structures, Zod/Pydantic input validation, error handling with isError flags, resource lifecycle management, and security practices. - Testing & Deployment: Unit and integration testing with InMemoryTransport, MCP Inspector debugging, and npm/pip/Docker distribution with client configuration examples. - Use Case: You want to expose your company's internal API to Claude. Use this Skill to scaffold the server, design well-described tools, validate inputs, test with the Inspector, and publish an npm package users can add to their MCP config. ## Quick Start Ask the AI to help you design and build an MCP server for your API following the mcp-builder methodology, starting with tool definitions and input schemas.

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 TypeScript?▼

Create a project with the @modelcontextprotocol/sdk and zod packages, register tools and resources in an entry index.ts, then connect the server via StdioServerTransport. Organize tools, resources, and client logic into separate directories for testability.

When should I use MCP Tools vs Resources vs Prompts?▼

Use Tools for operations with side effects like creating or deleting data, Resources for read-only data identified by URIs, and Prompts for predefined interaction templates that guide user workflows. The choice depends on whether the AI executes an action, reads data, or follows a template.

Why is my MCP tool not being called by the AI?▼

AI assistants select tools based on names and descriptions, so vague naming causes missed calls. Use snake_case verb-first names and descriptions that state the purpose, return content, and limits, and add .describe() annotations to every parameter.

How do I test an MCP server before deployment?▼

Write unit tests for tool logic as pure functions, then run integration tests using InMemoryTransport with the SDK Client to call tools end to end. Use the MCP Inspector via npx @modelcontextprotocol/inspector for interactive manual verification.

Why does console.log break my MCP server?▼

MCP servers communicate over stdio, so writing to stdout with console.log corrupts the protocol stream. Use console.error for debug output or the SDK's sendLoggingMessage method for structured logging instead.

How do I distribute an MCP server to users?▼

Publish to npm with a bin entry pointing to your compiled entry file, or to PyPI with a project.scripts entry point. Users then add a mcpServers configuration with the command, args, and environment variables such as API keys.

Related Skills

Explore More Software Engineering Skills→
nanocoainanocoai
30.5k

use-native-credential-proxy

Insert environment variable credentials into container API requests via a local proxy.

Official
Intermediate
wsimmondswsimmonds
109

vercel-ai-sdk

Integrate Vercel AI SDK v5 for chat interfaces, tool calling, and streaming.

Community
Advanced
heaptracetechnologyheaptracetechnology
13

api-test

Automate REST and GraphQL API testing against contracts and regressions.

Community
Advanced
berea-chberea-ch

generate-mcp-server

Generate an MCP server from an OpenAPI specification using the Speakeasy CLI.

Official
Advanced