Link Dump #223
A curated collection of articles on software architecture, AI tools, code quality, and developer psychology, exploring foundational concepts and modern challenges.
A curated collection of articles on software architecture, AI tools, code quality, and developer psychology, exploring foundational concepts and modern challenges.
Exploring how to build an AI-enhanced developer experience using centralized MCP servers, Skills, and tools to streamline workflows and agent access.
Introducing mcp-cli, a lightweight CLI tool for efficient, dynamic discovery and interaction with MCP servers, drastically reducing token usage for AI agents.
A developer's 2025 review: transitioning to a DevRel role at Pomerium, diving into security and AI agents via MCP, and giving numerous tech conference talks.
A guide on using MCPJungle as a proxy to connect local MCP servers (like Desktop Commander) remotely via Cloudflare Access for remote command execution.
Anthropic's Agent Skills specification becomes an open standard, detailing its lightweight design and current industry adoption.
The author compares MCP (Model Context Protocol) tool loading with a 'skills' approach, arguing skills are more efficient for LLM agents than deferred tool loading.
A developer automates ticket submission using Goose AI agent and Playwright MCP, integrating with a Chrome extension for seamless browser interaction.
A monthly tech link roundup covering AI agents, Kafka, Flink, LLMs, conference tips, and commentary on tech publishing trends.
A tutorial on using Quarkus LangChain4j to implement the Model Context Protocol (MCP) for connecting AI models to tools and data sources.
A developer explores using Claude Code and custom Skills to build a personal AI tool for managing and prioritizing a backlog of emails.
Explains how MCP servers enable faster development by using LLMs to dynamically read specs, unlike traditional APIs.
Argues that enterprises should use remote MCP servers instead of local stdio servers for better security, governance, and scalability with AI agents.
Analysis of MCP's advantages over OpenAPI, focusing on secure authentication and OAuth dynamic client registration for AI agents.
Anthropic proposes a new MCP approach that converts tools into executable code for more efficient AI agents, reducing token usage and errors.
A method using color-coding (red/blue) to classify MCP tools and systematically mitigate prompt injection risks in AI agents.
Explores integration methods between Microsoft Copilot and ServiceNow, covering Copilot 365, Copilot Studio agents, and MCP servers.
Learn to build AI agents in C# using Microsoft Agent Framework and Hugging Face MCP tools for image generation and analysis.
Explains the Model Context Protocol (MCP) by drawing parallels to RESTful HTTP architecture, using a travel planner server example.
A step-by-step tutorial on building a ChatGPT to-do app using the Model Context Protocol (MCP), JavaScript, Express, and React.