- Resources
- Courses & Learning
- Build with MCP
Courses & LearningFree
Build with MCP
Build a TypeScript MCP server with tools, resources, and prompts, move it to remote HTTP with authorization and security boundaries, then deploy and review it.
4 modules · 26 lessons. Readable online with no signup, or offline as a PDF or EPUB via the free newsletter.
View course (opens in new tab)Curriculum
- 1
Build a local TypeScript server
Create a typed stdio server with useful tools, errors, and logs.
- 01 Set up the TypeScript project
- 02 Create the notes data
- 03 Create the server factory
- 04 Add the search_notes tool
- 05 Add the get_note tool
- 06 Keep errors useful
- 07 Log without breaking stdio
- 08 Serve and inspect the local server
- 09 Check your understanding: build a stdio server
- 2
Add resources and prompts
Expose readable context and reusable prompt workflows deliberately.
- 10 Add a notes resource
- 11 Add a project review prompt
- 12 Design useful capability boundaries
- 13 Check your understanding: resources and prompts
- 3
Move to remote HTTP safely
Use the stateless protocol, authorization, and defensive boundaries.
- 14 Turn the factory into an HTTP handler
- 15 Understand stateless MCP
- 16 Authenticate and authorize requests
- 17 Protect secrets and limit access
- 18 Treat returned text as untrusted
- 19 Write a threat checklist
- 20 Check your understanding: remote HTTP and security
- 4
Deploy and review
Deploy the server, document both transports, and complete a security review.
- 21 Deploy to a web-standard runtime
- 22 Document local and remote setup
- 23 Run the final test matrix
- 24 Review the security boundary
- 25 Complete the project-notes server
- 26 Final check: deploy and review
Author
Flavio CopesMore from Flavio Copes
AI Agent Skills
Turn a repeated workflow into an Agent Skill, design its discovery and activation, write SKILL.md, bundle scripts, references, and assets, then evaluate, secure, and ship it.
AI Fundamentals
How language models work, writing prompts and project rules, curating context, agents and tools, verifying AI output, and using AI safely.
Build a Language Model on Your Mac
Train a small language model with Language Model Builder on a Mac. Covers tokens and embeddings, designing the run, pre-training and reading loss, fine-tuning with SFT and DPO, and comparing checkpoints in a lab report.
Local AI Models
Choose an open-weight model that fits your hardware, run it locally with Ollama and Node.js, build a private AI feature with structured output and fallbacks, and operate local AI responsibly.
MCP
What MCP solves, how hosts, clients, servers, tools, resources, and prompts fit together, and how to connect, configure, test, and troubleshoot an existing server you trust.
No resources match your search.