Model Context Protocol (MCP)

Gen AI · AI Agents & Tool Use

Theory

The Model Context Protocol (MCP) is an open standard for connecting AI applications to external tools and data, such as files, databases or business apps, through one common interface instead of a custom integration for every pair. An MCP server wraps a tool or data source and describes what it offers: tools the model can call, resources it can read and reusable prompts. An MCP client inside the AI application connects to servers, lists what they offer and passes those capabilities to the model.

Because the format is shared, one server built for a ticketing system can be reused by any compatible app or agent. This turns the "every app times every tool" integration problem into roughly "apps plus tools". MCP standardises the connection only; you still decide which servers to trust and what permissions each one gets.

Why we use it

Without a standard, every AI app needs its own connector for every tool, which multiplies work and maintenance. MCP lets a connector be written once and reused across many AI apps and agents.

When to use it

Use MCP when you want your tools or data available to several AI apps, or want to plug existing servers into your agent. For a single app calling one internal function, plain tool calling may be simpler.

How it works

  1. AI app starts with an MCP client
  2. Client connects to the configured MCP servers
  3. Client lists each server's tools and resources
  4. Model chooses a tool during the conversation
  5. Is the action allowed for this user? Yes: Call the server, return the result. No: Block or ask for approval.
  6. Model answers using the server's data

Example

Without MCP: build a custom integration between your AI app and Notion, another for Slack, another for GitHub — each from scratch.

With MCP: connect to an existing "Notion MCP server," a "Slack MCP server," and a "GitHub MCP server" — your agent instantly gains standardized access to all three, and any other MCP-aware app you build later can reuse the same servers.

Key points

Gen AI topics

Foundations of Generative AI

Prompt Engineering

Retrieval & Embeddings

Customizing Model Behavior

AI Agents & Tool Use

Multimodal & Applied AI

Ethics, Cost & Careers

T
Tech Town
Log InSign Up Free
Home SQL Python DSA Power BI Snowflake Databricks Spark Gen AI Practice Problems Contest Blog

Generative AI for the Data Stack

LLMs, prompt engineering, RAG, embeddings, agents and the tools shaping modern AI products — explained practically. Click any topic in the sidebar to open it right here.

{{ sectionCount }}
Sections
{{ topicCount }}
Topics
Free
Forever
Section {{ sec.num }}

{{ sec.label }}

Gen AI  /  {{ current.sectionLabel }}  /  {{ current.name }}

{{ current.name }}

💡

{{ current.tldr }}

Explained

{{ para }}

Why we use it

{{ rich.why }}

When to use it

{{ rich.when }}

Diagram

{{ rich.dg.caption }}

{{ tb.title }}
{{ c.v }}
{{ rich.dg.op }}
➜
{{ rich.dg.output.title }}
{{ c.v }}
{{ nd.label }}
{{ nd.sub }}
{{ nd.label }}
{{ nd.sub }}
{{ rich.dg.left.title }}
{{ it }}
{{ rich.dg.right.title }}
{{ it }}
Flowchart — how it works
{{ nd.text }}
{{ nd.text }}
◇ {{ nd.text }}
Yes → {{ nd.yes }}
No → {{ nd.no }}
See It In Action
{{ current.example }}
Key Takeaways — click to check off
{{ pt.mark }} {{ pt.text }}

Share this topic