← Back to live sessions
AG08Agentic AI

MCP: Model Context Protocol

Build an MCP server that exposes useful engineering tools and connect it to an AI client with clear tool contracts.

Production project

Internal Developer MCP Server

An engineering assistant needs standardised access to documentation search, service health, deployment details, and incident information.

Who this is for

  • •AI platform engineers integrating assistants with internal systems
  • •Developers who want reusable tool access across compatible AI clients

How this helps

  • •You can expose internal capabilities through a standard tool interface
  • •You understand the governance questions behind enterprise MCP adoption

What you will learn

The capabilities, not just the keywords.

  • •Explain MCP client/server responsibilities
  • •Expose tools through an MCP server
  • •Design tool descriptions and schemas for model use
  • •Connect a compatible AI client to the server
  • •Reason about permissions and safe enterprise tool exposure

Real production project

Internal Developer MCP Server

An engineering assistant needs standardised access to documentation search, service health, deployment details, and incident information.

What we build

  • •MCP server scaffold
  • •documentation-search tool
  • •service-status tool
  • •deployment lookup tool
  • •client integration

Stack

  • •TypeScript or Python
  • •MCP SDK
  • •AI client

Production concerns

  • •Authentication
  • •tool permissions
  • •secrets
  • •timeouts
  • •audit logs
  • •tenant boundaries

Finished deliverables

  • •Working MCP server
  • •tool contracts
  • •client connection
  • •security checklist

Prerequisites

Required

  • •Comfort with APIs and tool/function calling

Helpful, but optional

  • •AG01 or AG05
  • •TypeScript or Python backend experience

Before the session

Come ready to build.

  • •Node.js or Python
  • •Compatible MCP client setup
  • •Git

What to expect

15–25%Concept + problem framing
60–70%Implementation, design, and debugging
10–15%Production trade-offs + next actions

What you get

Something useful after the call ends.

  • •Source code
  • •MCP architecture diagram
  • •tool-design template
  • •production security notes

Where to go next

Tool Calling → MCP → Enterprise Agent Platforms

Every session can be booked independently. If you already know the prerequisite material, skip ahead.

Teaching proof

Review the evidence first.

See workshop delivery, technical projects, and teaching proof before booking.

Ready?

Request AG08: MCP: Model Context Protocol

Share your current level and what you want to build. The session can be adapted without changing its core outcome.

Request this session

FAQ

Can I book only this session?

Yes. Every session is designed to work independently.

Can I bring my own project?

Yes, when it fits the session outcome. We can map the concepts onto your project instead of the default example.

What if I already know part of the topic?

We can move faster through familiar material and spend more time on implementation, failure modes, and production trade-offs.

Is the session recorded?

Recording is not promised by default. Confirm this before the session if you need it.

What should I install?

The preparation section above lists the default setup. You will receive any session-specific setup notes before the call.

Are API or cloud charges included?

No. Any third-party API or cloud usage is paid directly through your own account unless explicitly agreed otherwise.