Module 3 of 7Lesson 1 of 1~17 min
MCP server, API integration, in-house tool or skill?
MCP is not always the right answer for connecting AI to a tool. This lesson gives you a short decision grid to compare an MCP server, a direct API integration, an in-house tool and a skill, taking context cost into account. You then apply it to your own needs.
Lesson objective
By the end of this lesson, you will be able to choose between an MCP server, a direct API integration, an in-house tool and a skill for a given need, based on four questions (who is the host, is the flow fixed, how many integrations, access or know-how) and on the context cost.
Topics covered
- MCP vs API
- Claude skills
- tool calling
- context window
- architecture choice
In the glossary
Where it fits
MCP or something else?
For this need, do you want an MCP server, an API integration, an in-house tool or a skill?
Lessons in this module
- MCP server, API integration, in-house tool or skill? (this lesson)
What you will learn in this module
This lesson is part of the course Connect AI to your tools and data with MCP
- Choose between an MCP server, a direct API integration, an in-house tool and a skill for a given need, and justify the choice.
Related courses
- AI & ProductAdvancedRegular practice: you already use the tools or work on this topic.
Build an AI assistant for your product
3 hr
- AI & ProductAdvancedRegular practice: you already use the tools or work on this topic.
Design a RAG architecture that fits your product
3 hr 30 min
- AI & ProductAdvancedRegular practice: you already use the tools or work on this topic.
Evaluate an AI feature: test sets, metrics and LLM judges
3 hr