What is mcp-development?

A guide to Model Context Protocol, an open standard for connecting AI assistants to outside tools and data sources.

Use it to develop MCP servers, connect clients, integrate external data and tools, and deploy MCP-based systems.

It explains how to build and connect shared tool integrations instead of creating a separate connection for every assistant and service.

mcp-development — Skill for Claude Code and Codex by fabioc-aloha

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add fabioc-aloha/Alex_Skill_Mall --skill mcp-development

Clone the repo

git clone --depth 1 https://github.com/fabioc-aloha/Alex_Skill_Mall

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/fabioc-aloha/alex_skill_mall/mcp-development/github.svg)](https://agentmods.dev/skills/fabioc-aloha/alex_skill_mall/mcp-development)

Your own site

<a href="https://agentmods.dev/skills/fabioc-aloha/alex_skill_mall/mcp-development"><img src="https://agentmods.dev/badge/skills/fabioc-aloha/alex_skill_mall/mcp-development/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/fabioc-aloha/alex_skill_mall/mcp-development"><img src="https://agentmods.dev/badge/skills/fabioc-aloha/alex_skill_mall/mcp-development.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 8 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 5,217 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00008	$0.05217
Opus 5	$0.00004	$0.02609
Sonnet 5	$0.00002	$0.01043
Haiku 4.5	$0.00001	$0.00522

Measured 8d ago against content hash 73c1466208ca, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

mcp-development scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

import { spawn } from "child_process";

plugins/ai-agents/mcp-development/skills/mcp-development/SKILL.md · 771 lines

How it starts

The opening of the file, as written. The whole thing — 771 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MCP Development Skill

Domain: AI Infrastructure Inheritance: inheritable Version: 1.2.0 Last Updated: 2026-03-10

⚠️ Staleness Watch (EXTERNAL-API-REGISTRY.md): MCP spec and SDK are actively versioned. SDK moved from 1.0.0 → 1.27.1 with 3 security fixes: cross-client data leak in shared instances (GHSA-345p-7cg4-v4c7), ReDoS (v1.25.2), command injection prevention (v1.27.1). New SDK features: task types, elicitation streaming, OAuth discovery/caching, fetch transport, conformance testing, framework-agnostic server refactoring. Streamable HTTP replaced HTTP+SSE for remote servers (spec 2025-03-26). Check MCP Changelog and SDK Releases when advising on transport or SDK usage.

Overview

Complete guide to the Model Context Protocol (MCP)—an open standard for connecting AI assistants to external data sources and tools. Covers architecture, server development, client integration, and production deployment patterns.

What Is MCP?

The Problem MCP Solves

Before MCP:
┌─────────┐     ┌─────────┐     ┌─────────┐
│ Claude  │     │ ChatGPT │     │ Copilot │
└────┬────┘     └────┬────┘     └────┬────┘
     │               │               │
     ▼               ▼               ▼
┌─────────┐     ┌─────────┐     ┌─────────┐
│Custom   │     │Custom   │     │Custom   │
│Plugin A │     │Plugin A'│     │Plugin A"│
└─────────┘     └─────────┘     └─────────┘
  (3 different implementations for same data source)

After MCP:
┌─────────┐     ┌─────────┐     ┌─────────┐
│ Claude  │     │ ChatGPT │     │ Copilot │
└────┬────┘     └────┬────┘     └────┬────┘
     │               │               │
     └───────────────┼───────────────┘
                     ▼
              ┌────────────┐
              │ MCP Server │  (One implementation, many clients)
              └────────────┘

Core Concepts

Concept	Description
Host	AI application (Claude Desktop, VS Code, etc.)
Client	MCP client within the host, manages server connections
Server	Provides tools, resources, and prompts via MCP
Transport	Communication layer (stdio, Streamable HTTP)

Read the full file on GitHub · 771 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

8d ago First seen · 771 lines · 8 tokens per session scan A 73c1466208ca

Subscribe to this mod's changes

mcp-development is a skill published in the GitHub repository fabioc-aloha/Alex_Skill_Mall (4 stars, last pushed today), licensed MIT. It adds 8 tokens to every session and 5,217 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Backend and APIs Building agents agentic-ai ai-assistant ai-skills best-practices github-copilot knowledge-base

azure-storage

UTILITY SKILL — Azure Storage Services: Blob, File Shares, Queue, Table, and Data Lake. Object storage, SMB shares, async messaging, NoSQL key-value, big-data analytics. Access tiers + lifecycle management. WHEN: "blob storage", "file shares", "queue storage", "table storage", "data lake", "access tiers", "lifecycle…

jonathan-vella/apex-accelerator · 105 tokens

api-design

REST API contract designer and reviewer. ALWAYS use when designing new endpoints, reviewing existing API contracts, planning API versioning, or standardizing error models. Covers resource modeling (URL/naming), HTTP method semantics, status code selection, error model consistency, pagination/filtering/sorting…

johnqtcg/awesome-skills · 123 tokens

mcp-development