Articles for people who
ship the stack
Original rewrites on React, Node.js, TypeScript and AI — practical notes from the same engineering practice behind our operator software. Article bodies are in English.
Tagged: MCP
MCP 2026-07-28: How the Stateless Spec Changes Remote Server Design
The MCP 2026-07-28 spec goes stateless: no sessions or handshake, plus MRTR, Tasks and cache hints. What changes for remote servers and how to migrate them.
23 min readYour Semantic Model Is the API: Giving Agents Certified Metrics
Why AI agents invent private definitions of revenue and inventory, and how a governed semantic model with grain, owners and refusals gives them one contract.
22 min readA Local LLM Agent Workflow Built From Folders and Markdown Files
Build a gated, multi-stage local agent pipeline where each stage is a folder, prompts are editable markdown, and a human reviews output before the costly step.
25 min readTen MCP Servers Worth Installing First, in Priority Order for Developers
A ranked starter set of MCP servers for AI coding assistants, from Context7 and GitHub to Postgres and memory, with install configs and permission cautions.
16 min readWebMCP in Practice: Turning a Task Board Into Tools for AI Agents
WebMCP in practice: a task board turned into tools for AI agents with declarative and scripted tools, a changing tool list, an MCP bridge and a refusal.
14 min readAgent Harness, Loop and Graph: Three Layers Behind Reliable AI Agents
Why unreliable agents are usually missing a layer: the harness around the model, an evidence-driven loop and an explicit graph, with code patterns and a debugging checklist.
15 min readMCP and OAuth2: Who Authorized the Agent's Action on Your MCP Server?
OAuth2 covers only part of agent authorization in the Model Context Protocol. How OIDC, scopes, confused-deputy rules, GNAP and capabilities fit together.
12 min readIs Your API Ready for AI Agents? A Practical MCP Readiness Checklist
Is your API ready for AI agents? An MCP readiness checklist: docs, schemas, authentication, which endpoints to expose, descriptions, testing and versioning.
12 min readSpring AI in the Enterprise: A Support Agent with Tools, RAG and Review
Spring AI for an incident-triage assistant: prompts as contracts, structured output, tool calling, MCP discovery, Qdrant RAG, tracing and bounded agent loops.
13 min read
About these articles
Request a 24h estimate
Need the same stack in a production operator layer? Send the brief — estimate within 24 hours.