MCP: guides & tutorials

Model Context Protocol (MCP) servers extend Claude Desktop and Claude Code with live access to external tools: Customer Relationship Management (CRM) data, web scraping, email, spreadsheets, and more. For marketing and sales teams, the right MCP server combination turns Claude into a research assistant, CRM manager, and content producer, all from a chat interface.

This guide covers 10 high-impact MCP servers for non-engineering business functions, with installation instructions and real-world usage examples. If you do not have a Claude account yet, you can try Claude free for a week and set these up the same day.

TL;DR:

Prerequisites:

• Claude Desktop installed (download)
• MCP works on Claude Free with usage limits; Claude Pro (~$20/mo) raises limits for heavier business use
• Budget 15+ minutes per server (OAuth / Google Cloud setup often takes longer than API-key-only servers)

Claude Desktop supports Model Context Protocol (MCP) servers and connectors for both free and paid users. For small teams, this means Claude Desktop is no longer just a chat window. With the right MCP servers it becomes a central operations hub that can read and act on Slack, Google Drive, Notion, CRM tools, and live web data without writing code.

This guide shows how Claude Desktop plus the right MCP servers can substitute for key workflows in five common paid SaaS tools (or significantly reduce your reliance on them), with setup instructions for non-technical teams and honest assessments of where this approach falls short. To be clear up front: MCP lets Claude Desktop work with these tools on your behalf. It does not literally delete every SaaS subscription, and we flag the cases where you still need the original tool.

TL;DR:

Prerequisites:

• Claude Desktop installed (download)
• Claude Free, Pro ($20/mo), or Team ($25/user/mo) subscription. MCP works on Free, but heavy daily use hits the message limits fast, so Pro or higher is realistic for business use. New to Claude? You can try Claude free for a week.
• 15 minutes per MCP server setup
• No app development required. You will edit a JSON (JavaScript Object Notation) config file and run npx commands in your terminal.

The Model Context Protocol (MCP) is the USB-C for AI: a single open standard that connects AI applications to tools, data sources, and workflows. Originated by Anthropic in late 2024 and now an open, community-maintained standard, MCP is supported across a wide range of clients (Claude Desktop and Claude Code, ChatGPT, VS Code, Cursor, and others). The specification covers two transports (local stdio and remote Streamable HTTP, which supersedes the older HTTP+SSE transport), server-side tools, resources, and prompts, and an OAuth 2.1-based authorization flow for remote servers. The public server ecosystem is large and growing fast, spanning official Anthropic servers, vendor servers, and community projects.

If you do not already use Claude, you can try Claude free for a week and follow along with every example in this handbook. The guide covers MCP server development end-to-end, from your first server to production deployment with authentication.

TL;DR:

Prerequisites:

• Node.js 18+ or Python 3.10+
• Claude Desktop or Claude Code installed
• Basic understanding of APIs and JSON

Model Context Protocol (MCP) is an open standard for how an AI host (IDE, desktop assistant, or similar) discovers and calls tools in a separate MCP server over transports such as stdio (local) or HTTP (remote). It is a JSON-RPC bridge that standardizes the boundary where models meet APIs, files, and automation. It does not replace your databases or scrapers. The payoff is one reusable integration surface across MCP-capable hosts, provided you still own auth, timeouts, and least privilege.

Below we split what the spec actually defines from what each vendor ships, sketch how the ecosystem shows up in scraping and data workflows, and outline adoption so a chat session does not become root access. For headline news context, see Top 10 AI and tech stories this week (March 17–24, 2026).

Production “agents” are mostly orchestration: LLM calls, tools, memory/state, retries, and guardrails. Three ecosystems lead in 2026—LangGraph, AutoGen, and CrewAI—each with different ergonomics for web data workloads.

Connect Apify to Claude Desktop via the official MCP server. Claude can run Actors from chat, browse the Apify Store, and read datasets, no code required. You ask; Claude scrapes. If you do not have the app yet, you can try Claude free for a week, then get an Apify account and follow the steps below.

The Model Context Protocol (MCP) is an open standard (originated by Anthropic, now community-governed) for connecting AI assistants like Claude (Desktop and Code), ChatGPT, VS Code, and Cursor to external tools. The ecosystem has grown quickly, with thousands of community-built servers now available. This guide covers the ones that are most useful for developers, with setup instructions and honest notes on when each fits.

Extended thinking first shipped in Claude 3.7 Sonnet (February 24, 2025), the first hybrid reasoning model from Anthropic. It is now standard across the Claude 4 family, and the model you should actually reach for today is Claude Sonnet 4.6 for balanced agent work or Claude Opus 4.7 when a task needs the strongest reasoning. Extended thinking lets the model reason through multi-step decisions before it acts, which is what makes Claude reliable for autonomous web research.

This guide covers the three main patterns for using Claude in web scraping and data collection workflows. The code works the same whether you point it at Sonnet 4.6 or Opus 4.7. Just swap the model ID.

Teams often want a shared MCP (Model Context Protocol) server: one deployment the whole team uses instead of each developer running a local server with their own API keys. MCP supports two transports. stdio runs the server as a local process, and remote MCP is reached over HTTP (the current spec uses Streamable HTTP, with older servers still on SSE). A self-hosted server on a VPS exposes its tools over HTTP and shows up in Claude as a remote MCP connector. This guide walks through provisioning a Liquid Web VPS, deploying your MCP server with PM2 or systemd, exposing it via Traefik over HTTPS, and connecting Claude to the remote endpoint with token-based auth. New to Claude? You can try Claude free for a week before committing to a paid plan.

Claude has built-in web search, which handles quick lookups well. What it does not do is targeted, structured scraping: pulling every product and price off a page, crawling a competitor's whole site, or returning a clean dataset you can process. That is where Apify comes in. The Apify MCP server turns 30,000+ Actors into Claude's tools, so you can ask Claude to run a scraper and it fetches the dataset straight into the chat. New to Claude? You can try Claude free for a week first. To wire up the data side, set up Apify MCP for Claude.