LLM on Simple Enough Blog

MCP Servers: Integration and Ecosystem

Wed, 17 Jun 2026 10:00:00 +0200

In the first article, we laid the groundwork for the Model Context Protocol; in the second, we built a server from end to end. That leaves the question that turns a prototype into an everyday tool: how do you integrate an MCP server into your working environment, reusing the existing ecosystem, without opening a security hole? That’s the subject of this final article.

I. Connecting a server to Claude and Claude Code

In the tutorial, we connected our server to Claude Desktop through claude_desktop_config.json. Claude Code, the command-line assistant, offers an even more direct approach with the claude mcp subcommand:

Tutorial: Building Your First MCP Server in Python

Wed, 10 Jun 2026 10:00:00 +0200

In the first article on Model Context Protocol servers, we laid the groundwork: its host / client / server architecture and its three primitives (tools, resources, prompts). Now for the practical part. In this tutorial, we build a small MCP server in Python from end to end, exposing one tool and one resource, then we connect it to a host to watch a model use it.

I. Prerequisites and installation

You need Python 3.10 or higher. The official SDK also ships a handy command-line utility to test and install a server.

MCP Servers: Understanding the Model Context Protocol

Wed, 03 Jun 2026 10:00:00 +0200

Language models are brilliant at reasoning over text, but by nature they are cut off from the world. A model cannot read your files, query your database, or call an API unless it is explicitly given the means to do so. The Model Context Protocol (MCP) is the standard that solves this problem in a generic way. This first article lays the groundwork; the next ones will dive into building a server and integrating it into an ecosystem.

What is a Harness for AI Agents? Understanding the Infrastructure Behind Claude Code and Cursor

Wed, 27 May 2026 15:55:01 +0200

I. What is a Harness for AI Agents?

When you first discover tools like Claude Code, Cursor, or OpenAI Codex, it is easy to assume that a simple language model is capable of understanding an entire codebase, fixing bugs, executing commands, and running tests autonomously.

However, the technical reality is far more interesting.

The AI model is often only one piece of the system. Behind these tools lies a much more important layer than it first appears: the harness.

Writing a Prompt: Technical Guide

Fri, 18 Apr 2025 11:02:00 +0100

I. Understanding What a Prompt Is in LangChain

In LangChain, a prompt is a textual structure designed to guide a language model. A well-constructed prompt includes several key components:

Instruction: What you explicitly ask the model to do.
Context: Additional information to frame the answer.
Input Data: The specific input provided at runtime.
Output Indicator: What kind of output is expected.

This format enables clear, framed, and reproducible queries.
Here’s another example using LangChain in Python with this structure:

Hallucinating with LangChain

Mon, 07 Apr 2025 09:22:00 +0100

I What is a hallucination?

A hallucination refers to a response generated by a language model that is factually incorrect, invented, or misinterprets reality. It can range from a minor inaccuracy to a completely fabricated citation or even a made-up technical or historical claim.

Example:

“Einstein discovered general relativity in 1975.”

That’s incorrect (it was in 1915), but the model might produce this kind of statement if it lacks the proper context or is too confident in its reasoning.

1000: The Magic Number in the World of LLMs

Wed, 26 Mar 2025 09:05:00 +0100

I. Chunk Size: Why ~1000 Tokens?

The default value of 1000 tokens per chunk is not arbitrary:

A chunk of this size generally contains enough information to remain semantically coherent without being too large.
It remains compatible with the context window of modern LLMs (4k, 8k, 32k, or even 1M tokens).
It helps avoid diluting meaning or breaking semantic units.

In some cases, other sizes may be more appropriate: