Agentic AI Private

Model Context Protocol (MCP) for Connecting Agents to Enterprise Systems (AGNTDV103)

2 days
Agentic AIAI

Build secure Model Context Protocol servers that connect AI agents to databases, internal APIs, and document stores with proper auth and least privilege.

Talk to a Learning ConsultantRequest a Private Class

Register or Request Training

  • Private class for your team
  • Live expert instructor
  • Online or on‑location
  • Customizable agenda
  • Proposal responses same day as request
Request Proposal

Course Overview

Every agent project eventually hits the same wall: each new system means another bespoke integration, another auth story, and another set of tools nobody else can reuse. The Model Context Protocol standardizes that layer — one protocol for exposing tools, data, and prompts to any MCP-capable client.

This course is a working engineer's treatment of MCP. Students learn the protocol itself — transports, lifecycle, tools, resources, prompts, sampling, and elicitation — then build servers that front real enterprise systems: a relational database, an internal HTTP API, and a document store. The emphasis is on the parts that decide whether an MCP integration is safe to deploy: authorization and token handling, scoping tools to least privilege, auditing, and the prompt-injection exposure that comes with giving a model access to internal data.

Students finish with servers of their own, connected to live agent clients, plus a clear-eyed view of when MCP is the right abstraction and when a plain function call is better.

Who should attend: Platform engineers, integration developers, and architects responsible for connecting AI systems to internal data and services.

Course Benefits

  • Explain the MCP architecture, message flow, and lifecycle precisely
  • Build MCP servers exposing tools, resources, and prompts over stdio and HTTP transports
  • Design tool interfaces a model can actually use correctly
  • Implement authentication and authorization, including OAuth flows and per-user token scoping
  • Front databases, internal APIs, and document stores with safe, least-privilege servers
  • Reason about prompt injection, data exfiltration, and confused-deputy risk in tool-mediated access
  • Test, version, deploy, and monitor MCP servers
  • Decide when MCP is warranted versus a direct integration

Delivery Methods

Private Class
Delivered for your team at your site or online.

Course Outline

  • Day 1 — Protocol and Server Development
    • Module 1: The Integration Problem MCP Solves
      • The N×M integration problem in agent platforms
      • MCP architecture: hosts, clients, servers, and who trusts whom
      • What MCP standardizes and what it deliberately leaves to you
      • When not to use MCP
    • Module 2: Protocol Mechanics
      • JSON-RPC foundation, initialization, capability negotiation, and versioning
      • Transports: stdio for local, streamable HTTP for remote; trade-offs and deployment implications
      • Primitives: tools, resources, and prompts — and which to reach for
      • Server-initiated features: sampling, elicitation, roots, and logging
    • Module 3: Designing Tools a Model Uses Correctly
      • Naming, descriptions, and schemas as the real interface
      • Granularity: few powerful tools vs. many narrow ones
      • Returning results: shape, size limits, truncation, and pagination
      • Error design: actionable messages the model can recover from
      • Idempotency, dry-run modes, and destructive-action annotations
  • Day 2 — Enterprise Integration, Security, and Operations
    • Module 4: Authentication and Authorization
      • Local servers and credential handling
      • Remote servers: OAuth 2.1, authorization servers, resource indicators, and token audience
      • Acting as the user vs. acting as a service account; impersonation risks
      • Per-user scoping, consent, and token lifetime
      • Secret management and what never belongs in a tool argument
    • Module 5: Security of Tool-Mediated Access
      • Prompt injection through retrieved content and tool results
      • Data exfiltration paths; the lethal trifecta of private data, untrusted content, and external communication
      • Confused-deputy problems and over-broad scopes
      • Defenses: least privilege, allowlists, human confirmation, output sanitization, and egress control
      • Auditing: logging every tool invocation with identity and arguments
    • Module 6: Enterprise Systems in Practice
      • Patterns for document stores, ticketing, CRM, data warehouses, and observability platforms
      • Combining MCP with RAG: retrieval as an MCP resource or tool
      • Multiple servers in one host: namespacing, tool-count pressure, and context cost
      • Server composition and gateway patterns
    • Module 7: Testing, Deployment, and Operations
      • Testing servers without a model in the loop
      • Contract tests and schema change management
      • Packaging and distribution; versioning and deprecation
      • Deploying remote servers: containers, scaling, and statelessness
      • Monitoring: call volume, latency, error rates, and cost per tool

Class Materials

Each student receives a comprehensive set of materials, including course notes and all class examples.

Class Prerequisites

Experience in the following is required for this Agentic AI class:

  • Python or TypeScript proficiency
  • Familiarity with REST and OAuth
  • Basic agent or LLM tool-calling experience, such as from Building AI Agents with LangGraph and LangChain (AGNTDV101) or equivalent

Prerequisite Courses

Courses that can help you meet these prerequisites:

Have questions about this course?

We can help with curriculum details, delivery options, pricing, or anything else. Reach out and we’ll point you in the right direction.

Talk to a Learning Consultant