If you're wiring up MCP servers or clients to connect Claude with external tools and data sources, this walks you through the full cycle: scaffolding projects with the TypeScript or Python SDKs, defining tool schemas with Zod or Pydantic, configuring stdio/HTTP/SSE transports, and debugging protocol compliance with the inspector. The minimal working examples show a weather tool and resource provider in both languages, complete with validation and proper JSON-RPC responses. It's opinionated about security (never skip auth, rate limiting, or input validation) and includes a reference guide that points to protocol specs and SDK docs. Useful if you're building integrations and want guardrails around the finicky bits of schema validation and transport setup.

skills.sh installs
4.4K
GitHub stars
12.3K
last updated
Aug 21, 2026

Install

$ npx -y skills add jeffallan/claude-skills --skill mcp-developer --agent claude-code

Installs into .claude/skills of the current project.

Files

MCP Developer

Senior MCP (Model Context Protocol) developer with deep expertise in building servers and clients that connect AI systems with external tools and data sources.

Core Workflow

  1. Analyze requirements — Identify data sources, tools needed, and client apps
  2. Initialize project — npx @modelcontextprotocol/create-server my-server (TypeScript) or pip install mcp + scaffold (Python)
  3. Design protocol — Define resource URIs, tool schemas (Zod/Pydantic), and prompt templates
  4. Implement — Register tools and resource handlers; configure transport (stdio/SSE/HTTP)
  5. Test — Run npx @modelcontextprotocol/inspector to verify protocol compliance interactively; confirm tools appear, schemas accept valid inputs, and error responses are well-formed JSON-RPC 2.0. Feedback loop: if schema validation fails → inspect Zod/Pydantic error output → fix schema definition → re-run inspector. If a tool call returns a malformed response → check transport serialisation → fix handler → re-test.
  6. Deploy — Package, add auth/rate-limiting, configure env vars, monitor

Reference Guide

Load detailed guidance based on context:

Sponsors

Details

Repository
github.com/jeffallan/claude-skills
Categories
Backend & APIs, AI & Agent Building, Debugging, Automation & Workflows, Python

More from jeffallan/claude-skills

All 66
1medusajs avatarbuilding-storefrontsmedusajs/medusa-agent-skillsLoad automatically when planning, researching, or implementing Medusa storefront features (calling custom API routes, SDK integration, React Query patterns, dat4.4Kskills.sh installs
2giuseppe-trisciuoglio avatartypescript-docsgiuseppe-trisciuoglio/developer-kitGenerates comprehensive TypeScript documentation using JSDoc, TypeDoc, and multi-layered documentation patterns for different audiences. Use when creating API d4.4Kskills.sh installs
3getsentry avatargh-review-requestsgetsentry/skillsFetch unread GitHub notifications for open PRs where review is requested from a specified team or opened by a team member. Use when asked to "find PRs I need to4.3Kskills.sh installs
4starchild-ai-agent avatarcomposiostarchild-ai-agent/official-skillsComposio gateway: act on 1000+ connected apps like Gmail, Slack, GitHub, Calendar. Use when the user wants to act in a connected SaaS app (e.g. send Gmail, crea4.3Kskills.sh installs
5dpearson2699 avatarswiftui-liquid-glassdpearson2699/swift-ios-skillsImplement, review, or improve SwiftUI Liquid Glass effects for iOS 26+. Covers glassEffect modifier, GlassEffectContainer, glass button styles, glass toolbar/ta4.3Kskills.sh installs
6nomadamas avatartoss-securitiesnomadamas/k-skill토스증권 조회형 질문을 공식 Open API(OAuth2)로 우선 처리하고, 공식 credentials가 없으면 tossinvest-cli의 tossctl을 fallback으로 써서 계좌, 보유주식, 시세/종목/시장정보, 주문조회를 안전한 read-only 흐름으로 조회한다. 돌쇠에서는4.3Kskills.sh installs