Action guide
Build a Hacker News MCP server from scratch
From zero to a real MCP server. FastMCP. Real tools. A desktop client path. MCP reads like any other service you ship because it is one.
Get the full guide
Free newsletter unlocks the full guide and subscriber links. Same library working engineers use. No pedigree bingo.
Free. No spam. Unsubscribe anytime.
Why subscribe
Tutorials quit after 'it printed JSON.' You need a server you can run, break, and extend. MCP stops being magic once it looks like every other integration you already wrangled.
For: Engineers shipping tools into LLM clients who care about real HTTP, errors, retries. Not slide decks.
- An end-to-end path from empty folder to running MCP server
- A grounded map of host, client, and tool responsibilities
- Patterns you can steal for the next integration
- Full build with concrete file-level detail
- FastMCP plus tool wiring against a live API
- Extension ideas that survive a skeptical reviewer
- Uses Hacker News because it fails like production APIs fail
Subscribe free to unlock the full guide and all future updates.
What you’ll learn
What MCP is for in practice, how to define tools the model can call (search stories, pull comments), and how a small Python/FastMCP server exposes them so a client like Claude Desktop can plan, call tools, and synthesize an answer-using Hacker News as the concrete API surface.
When you subscribe to the newsletter, you get access to the full online guide alongside course and issue updates.
Explore the other action guides
Each guide kills one sharp problem. You leave with steps you can type, not inspiration quotes.
-
AI Agent Architecture Simplified
'Just add an agent' turned into spaghetti. Here is the ReAct loop you can actually fit in your head. Reason. Act. Observe. Then wire state and tools like a real system.
View guide →
-
Attention: Explained for Engineers
Attention still looks like matrix soup. Here is what Q, K, and V actually do. Why it scales ugly. How to use that when you size context and money.
View guide →
-
Bayes' Theorem Made Simple
Bayes shows up in papers and evals and you freeze. Here is a visual path through priors, likelihoods, and evidence. Plain vocabulary. No stats degree required.
View guide →
-
Build a Research Agent in LangChain
The smallest LangChain stack for a ReAct research loop. Chat model. Tools. Scratchpad prompt. Executor. Skip drowning in framework trivia.
View guide →
-
DocString and Review Agent in LangGraph
Your agent never knows when to stop. LangGraph with typed state, nodes, edges, and conditional loops. Real design instead of a prayer loop.
View guide →
-
How LLMs Tokenize Text
Billing and limits disagree with your word count. Rare names and compounds blow up. Tokenization hits cost and quality like a tax you did not see coming.
View guide →
-
How MCP Works
How host, client, and server really connect in MCP. Integrate and debug like you own the wire, not like a tourist squinting at JSON.
View guide →
-
Prompt LLMs Like a Pro by Context Activation
Longer prompts made outputs worse. Word choice wakes the right slice of training. Stop building walls of text nobody reads.
View guide →
-
Setting Up AI Projects in Python
Your AI repo outgrew the demo script. Env files, pyproject, src layout, and a clean split between HTTP surfaces and agent code.
View guide →
-
Tests That Mean Something
Outputs drift. Your suite shrugs. Here are unit tests that pin behavior you actually care about. Skip the ceremony that only pads ego.
View guide →
-
Understand RAG From First Principles
Naive RAG parrots garbage. Your pile of docs is huge. The model’s window is not. Every extra token hits the invoice. Own the data path or keep paying for lies.
View guide →
-
Write System Prompts for AI Agents Like a Pro
When your system prompt is a novel and the agent still veers: what is already baked into models, and what to add so your instructions carry real signal.
View guide →