How to Add an MCP Server to Claude Code: Step-by-Step
How to add an MCP server to Claude Code with claude mcp add: hosted, local and OAuth servers, scopes, .mcp.json, status checks and fixes for common errors.
10 min read
SubmitLog in
Blog
A collection of useful articles for developers and software enthusiasts. Learn about the latest trends and technologies in the community.
Agentic Workflows: 5 Patterns and When to Use Each
Agentic workflows let a model choose its next step at runtime. Five patterns from Anthropic and LangGraph, real GitHub and IBM examples, and when to skip them.
8 min read
7 Open Source AI Agents Worth Building On in 2026
A comparison of open source AI agents: LangChain, CrewAI, OpenHands, goose, AutoGPT, Dify and n8n, with real license terms and 2026 release dates.
7 min read
Voice AI Agents Explained: How They Work and Who's Building One
Voice AI agents handle spoken calls with an LLM instead of a script. How the STT-LLM-TTS pipeline works, who builds voice AI agents, and what's new.
6 min read
What Is an MCP Client? How Hosts, Clients and Servers Fit
What is an MCP client? It is the part inside apps like Claude, Cursor and VS Code that opens one connection to one MCP server to fetch tools and data.
6 min read
Human in the Loop AI Agents: How HITL Works and When to Use It
Human in the loop AI agents pause before a risky action so a person can approve, reject or edit it. How the pattern works, real frameworks, and when to skip it.
5 min read
MCP Server Security: How to Secure MCP Servers in 2026
MCP server security covers confused deputy attacks, token passthrough, tool poisoning and supply chain risk, and how to harden a Model Context Protocol server in 2026.
5 min read
MCP Server Registry Explained: What It Is and How It Works
An MCP server registry catalogs available MCP servers so clients like Claude and Cursor can find and connect to them. Here is how one actually works.
3 min read
AI Agent Evaluation: How to Test and Score Agents in 2026
AI agent evaluation tests an agent's plans, tool calls and outcomes with code, model and human graders. How it works, real examples and what changed in 2026.
7 min read
AI Agent Memory: How It Works and What to Use in 2026
AI agent memory lets an agent recall facts and history across sessions. Here is how it works, the main frameworks, and when you actually need it.
2 min read
How to Submit Your AI Agent to a Directory
Learn how to submit your AI agent, MCP server, or skill to AI Agents Listing: prerequisites, form fields, pricing, and common rejection reasons.
9 min read
Computer Use Agents Explained: How AI Operates a Desktop
Computer use agents let an AI model click, type and navigate a real screen. Here is how they work, the leading tools, and where they still fail.
4 min read
AI Agent Observability Tools: 7 Options Compared
A comparison of AI agent observability tools for tracing, evaluating and monitoring agents in production, with pricing, licensing and what each one covers.
8 min read
Multi-Agent Systems Explained: How They Actually Work
Multi-agent systems split one task across several LLM agents. Here is how coordination, delegation and context sharing actually work, with 2026 data.
7 min read
Agentic RAG Explained: How AI Agents Make Retrieval Smarter
Agentic RAG wraps retrieval-augmented generation in an agent's control loop. Here is how it works, what changed in 2026, and when it is worth the cost.
6 min read
LangGraph vs CrewAI: Which Orchestration Framework in 2026
LangGraph vs CrewAI compared for AI agent orchestration, plus Microsoft Agent Framework, OpenAI Agents SDK and Google ADK, with what shipped in 2026.
5 min read
Agent to Agent Protocol (A2A): What It Is and How It Works
The agent to agent protocol (A2A) lets AI agents from different vendors discover, delegate to and track each other's work. Here is how it works in 2026.
7 min read
MCP vs Function Calling: A Maker's Decision Guide
MCP vs function calling compared with concrete decision rules, tradeoffs and a hybrid architecture, for makers choosing which to build with.
7 min read
5 Agentic AI Coding Tools Compared for Developers
A curated list of five agentic AI coding tools — Claude Code, Cursor, OpenAI Codex CLI, Aider, and OpenCode — and how to choose one for your workflow.
6 min read
Agentic OS Explained: What It Is and Who's Building One
An agentic OS extends scheduling, memory, and permissions to AI agents. Here's what the 2026 papers and open-source projects are building.
8 min read
The Best MCP Servers Worth Installing in 2026
A curated, decision-ready list of the best MCP servers for docs, browser automation, and databases, with transport and install notes for each.
7 min read
How to Build an AI Agent: A Developer's Step-by-Step Tutorial
A code-first tutorial on how to build an AI agent: the three core components, MCP tools, orchestration patterns, and when to skip agents entirely.
9 min read
Claude Skills Explained: How SKILL.md Files Teach an Agent a Job
Claude Skills are folders with a SKILL.md file that Claude loads on demand. How they work, where they run, every frontmatter field, and what changed in 2026.
9 min read
Browser Agents: 11 Tools That Let an AI Agent Use the Web
Browser agents compared: Browser Use, Stagehand, agent-browser, Playwright MCP, Browserbase, Browserless, Cloudflare Browser Run, Firecrawl and more, with prices.
11 min read