Course Objective & Scope
MCP (Model Context Protocol) connects enterprise systems to clients such as Claude, ChatGPT, VS Code and Cursor, and to your own agents, through a single standard interface. This course covers the protocol's architecture and the steps for turning an internal system into a secure MCP server.
Labs cover defining tools, resources and prompts with the Python and TypeScript SDKs, the stdio and Streamable HTTP transports, authorisation with OAuth 2.1, testing with MCP Inspector and client-side integration. The output is a working MCP server for a system chosen by the organisation, plus a security checklist.
Who Should Attend?
- Backend developers who will expose internal systems to AI assistants
- AI engineers building agent applications
- Integration and API platform teams
- Prerequisite: Python or TypeScript and API development experience
Key Takeaways
- Explain the MCP architecture (host, client, server) and its lifecycle
- Develop an MCP server that exposes tools, resources and prompts
- Set up Streamable HTTP and OAuth authorisation for remote servers
- Discover and use tools through an MCP client in your own agent
- Harden the server against prompt injection and excessive permissions
Curriculum
MCP Architecture
- Host, client and server roles, JSON-RPC messaging
- Tools, resources, prompts and client features such as sampling and elicitation
A First MCP Server
- Defining tools with the Python SDK (FastMCP) and the TypeScript SDK
- The stdio transport and connecting to desktop clients
- Testing with MCP Inspector
Remote Servers and Authorisation
- The Streamable HTTP transport and session management
- OAuth 2.1-based authorisation and enterprise identity providers
Building an MCP Client
- Coding a client for tool discovery and invocation
- Connecting multiple servers to one agent
Security and Operations
- Tool poisoning, prompt injection and excessive permission risks
- Logging, rate limiting and server versioning
- Server project and checklist for an organisational system
Other Courses in This Category
-
Designing multi-agent systems with supervisor, hierarchical, orchestrator-worker and swarm patterns: context isolation, task routing, cost control and a comparison of LangGraph, CrewAI and Microsoft Agent Framework.
- Live Course
- 5 modules
-
Hands-on training on designing working, episodic, semantic and procedural memory layers for AI agents using context summarisation, vector and graph memory stores, memory consolidation and retention policies.
- Live Course
- 5 modules
-
Technical course on safely executing LLM- and agent-generated code using gVisor, Firecracker microVMs, container isolation, network/filesystem restrictions and resource quotas.
- Live Course
- 5 modules
-
Course on evaluating end-to-end task completion, trajectory quality and tool selection in AI agents, and setting up distributed tracing and live monitoring with OpenTelemetry, LangSmith, Arize Phoenix and Langfuse.
- Live Course
- 5 modules
-
Training on protecting multi-step agents against API outages, rate limits, partial failures and crashes using retries, model fallbacks, idempotency, compensating actions and durable execution with Temporal and LangGraph.
- Live Course
- 5 modules
-
Architectural design course examining prompt chaining, routing, parallelisation, orchestrator-workers, evaluator-optimizer and autonomous agent patterns, and how to pick the simplest effective pattern for each problem.
- Live Course
- 5 modules
Get in touch
