AIUnlimited
🌳

KI-Grundlagen

🌱
AI Seeds

Starte bei null

🌿
AI Sprouts

Fundament aufbauen

🌳
AI Branches

In der Praxis anwenden

🏕️
AI Canopy

In die Tiefe gehen

🌲
AI Forest

KI meistern

🔨

KI-Meisterschaft

✏️
AI Sketch

Starte bei null

🪨
AI Chisel

Fundament aufbauen

⚒️
AI Craft

In der Praxis anwenden

💎
AI Polish

In die Tiefe gehen

🏆
AI Masterpiece

KI meistern

📘

KI-Praxis

📖
Open-Source-Modelle verstehen

Grundlagen und Ressourcen für Open-Source-Modelle

🎯
Vom Problem zur Modellaufgabe

Geschäftsprobleme in Modellaufgaben umwandeln

⚡
Ihr erstes Modell ausführen

Sehen Sie Ihre ersten Ergebnisse in 30 Minuten

🔧
Fine-Tuning und Evaluierung

Modelle feinjustieren und Leistung bewerten

🚀
Anwendungssysteme

Bauen Sie reale KI-Anwendungen

🎨
Generative KI

Erkunden Sie Open-Source-AIGC-Modelle

🤖
Agenten

Lernen Sie Agent-Frameworks und MCP-Werkzeuge

📐
Ergänzende Grundlagen

LLM-Grundlagen und Evaluierung

🎓

Claude Akademie

🤖
Claude 101

Learn AI basics with Claude

💻
Claude Code 101

Code with Claude as your pair programmer

🤝
Introduction to Claude Cowork

Collaborate with Claude on complex projects

⚙️
Claude Platform 101

Build apps with the Claude API

Labor

7 Experimente geladen
🧬Neuronales Netz Sandbox🤖KI oder Mensch?🥋Prompt Engineering Dojo🏁Algorithmus-Rennen🧠KI-Quizduell🏗️Systemdesign-Leinwand
🎯ProbeinterviewLabor betreten→
🚀

Karriereentwicklung

🚀
Interview-Startrampe

Starte deine Reise

🌟
Verhaltensinterview-Meisterschaft

Soft Skills meistern

💻
Technische Interviews

Die Coding-Runde bestehen

🤖
AI- & ML-Interviews

ML-Interview meistern

🏆
Angebot & Karriere

Das beste Angebot sichern

Loslegen
AIUnlimited

MIT-Lizenz

沪ICP备18025655号-11

Lernen

  • KI-Grundlagen
  • KI-Praxis
  • Claude Akademie
  • Labor
  • Karriereentwicklung

Community

  • Über uns
  • FAQ

Unterstützung

  • Nutzungsbedingungen
  • Datenschutzerklärung
  • Kontakt
KI & Engineering Programme›💻 Claude Code 101›Lektionen›MCP
🔌
Claude Code 101 • Fortgeschritten⏱️ 6 Min. Lesezeit

MCP

MCP

Model Context Protocol (MCP) is an open standard that lets Claude Code connect to external tools and data sources. When you ask a question, Claude automatically understands when it should use those tools to better handle your query.

A lot of your context lives outside your codebase — in databases, productivity apps, or public repositories. MCP bridges that gap.

What Can You Do With It?

First, it's important to understand the concept of "tools" in agentic AI. Tools give agents like Claude Code the ability to perform actions that help them complete tasks more effectively. This is different from typical AI, where you just get a text response back.

For example, if your team uses Linear for project management, you can add a Linear MCP server to bring in the details of your specific issues. If you need up-to-date documentation for a dependency, a docs MCP server like Context7 can provide that to Claude Code.

Adding an MCP Server

You can add MCP servers with the claude mcp add command. There are two main types:

  • HTTP servers are for remote services. These are hosted by the service provider and connect over the network.
  • Stdio servers are for local processes that run on your machine.

You can manage your servers with /mcp inside a Claude Code session to see what's connected, check status, and disable servers you don't need.

Scoping Servers

MCP servers can be scoped in three ways:

  1. Local — only available in the current project, just for you.
  2. User — available across all your projects.
  3. Project — uses a .mcp.json file that you check into version control so anyone on the codebase gets the exact same servers automatically.

Context Costs

MCP servers add tool definitions to your context window — even when you're not actively using them. If you have a lot of servers configured, this eats into your available context. Run /mcp to see what's connected and disable anything you're not actively using.

If a tool has a CLI equivalent (like for GitHub or for AWS), the CLI is more context-efficient because it doesn't add persistent tool definitions.

Lektion 11 von 120% abgeschlossen
←Skills

Diskussion

Anmelden an der Diskussion teilnehmen

gh
aws

You might also benefit from using a Skill instead. A Skill has a name and description loaded into context, and Claude only loads the full skill contents when it determines it needs to use it.

If your MCP tools exceed 10% of your context window, Claude Code automatically switches to tool search mode, which discovers the right tools on demand — though this may not work as reliably.

Recap

MCP connects Claude Code to your external tools and data sources. Add servers with claude mcp add. Scope them to your project with .mcp.json so your team gets them automatically. And keep an eye on context usage by disabling servers you're not actively using.