AIUnlimited
🌳

Fondations IA

đŸŒ±
AI Seeds

Partez de zéro

🌿
AI Sprouts

Construisez les fondations

🌳
AI Branches

Mettez en pratique

đŸ•ïž
AI Canopy

Approfondissez

đŸŒČ
AI Forest

MaĂźtrisez l'IA

🔹

MaĂźtrise IA

✏
AI Sketch

Partez de zéro

đŸȘš
AI Chisel

Construisez les fondations

⚒
AI Craft

Mettez en pratique

💎
AI Polish

Approfondissez

🏆
AI Masterpiece

MaĂźtrisez l'IA

📘

Pratique IA

📖
Comprendre les modĂšles open-source

Fondamentaux et ressources pour les modĂšles open-source

🎯
Du problĂšme Ă  la tĂąche modĂšles

Transformer les problÚmes métier en tùches modÚles

⚡
Exécuter votre premier modÚle

Voyez vos premiers résultats en 30 minutes

🔧
Fine-tuning et évaluation

Affinez les modÚles et évaluez les performances

🚀
SystĂšmes d'application

Construisez des applications IA réelles

🎹
IA générative

Explorez les modĂšles AIGC open-source

đŸ€–
Agents

Apprenez les frameworks Agent et outils MCP

📐
Fondamentaux supplémentaires

Bases LLM et évaluation

🎓

Claude Académie

đŸ€–
Claude 101

Learn AI basics with Claude

đŸ’»
Claude Code 101

Code with Claude as your pair programmer

đŸ€
Introduction to Claude Cowork

Collaborate with Claude on complex projects

⚙
Claude Platform 101

Build apps with the Claude API

Labo

7 expériences chargées
🧬Bac Ă  sable neuronalđŸ€–IA ou Humain ?đŸ„‹Dojo d'ingĂ©nierie de prompts🏁Course d'algorithmes🧠Quiz IAđŸ—ïžCanevas de conception systĂšme
🎯Entretien simulĂ©Entrer dans le labo→
🚀

Développement de carriÚre

🚀
Rampe de lancement entretien

Commencez votre parcours

🌟
MaĂźtrise comportementale

Maßtrisez les compétences relationnelles

đŸ’»
Entretiens techniques

Réussissez l'épreuve de code

đŸ€–
Entretiens IA et ML

MaĂźtrisez l'entretien ML

🏆
Offre et au-delĂ 

Décrochez la meilleure offre

Commencer
AIUnlimited

Licence MIT

æČȘICP怇18025655ć·-11

Apprendre

  • Bases de l'IA
  • Pratique IA
  • Claude AcadĂ©mie
  • Labo
  • DĂ©veloppement de carriĂšre

Communauté

  • À propos
  • FAQ

Soutien

  • Conditions d'utilisation
  • Politique de confidentialitĂ©
  • Contact
Programmes d'IA et d'ingĂ©nierieâ€șđŸ’» Claude Code 101â€șLeçonsâ€șMCP
🔌
Claude Code 101 ‱ IntermĂ©diaire⏱ 6 min de lecture

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.

Leçon 11 sur 120% terminé
←Skills

Discussion

Se connecter pour rejoindre la discussion

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.