The Appnova blog
Field notes.
Practical writing on MCP, multi-agent orchestration, and the tools we ship. No hype, no think-pieces — just what we learned while building.
RSS feed- 11 min read
AI agent orchestration in practice: a control plane for your local coding agents
Running five AI coding agents across tmux tabs is chaos. A control-plane design for orchestrating them in parallel — and how to know when an agent is actually done.
AI agent orchestrationmulti-agentsystem design Read → - 6 min read
How to choose a trustworthy MCP server: a security-first comparison
Connecting an MCP server hands an AI agent real permissions. Here's a security-first way to compare the big directories — and why vetting beats catalogue size.
MCPsecuritycomparison Read → - 4 min read
The 2026 MCP Directory Landscape
There are five big places developers go to find MCP servers in 2026 — and they are wildly different sizes. A field guide, with real numbers.
MCPecosystemfield notes Read → - 5 min read
How to coordinate Claude, GPT, and Gemini in one workflow
Multi-agent orchestration in plain terms: route each part of a task to the model that's best at it, pass the results between them, and keep one shared context.
multi-agentorchestrationguide Read → - 4 min read
What is an MCP server (and how to choose one)
An MCP server is a small program that gives an AI agent real tools and data through the Model Context Protocol. Here's what it does — and how to pick a good one.
MCPexplainerguide Read →