Building Coordination Infrastructure: What 32 MCP Servers Without a Bus Look Like
Thirty-two MCP servers for Kenya's coordination domains. Water. Health. Agriculture. Insurance. Land. Education. Transport. Tax. Labor. Market prices.…
Team Management
⚑ Report a ProblemLatest Team Management news from Tech News
All topics
Culture
agents
ai
api
architecture
automation
beginners
career
claude
devchallenge
devops
discuss
javascript
llm
machinelearning
mcp
opensource
productivity
programming
python
react
saas
security
showdev
softwareengineering
startup
testing
tutorial
typescript
webdev
Why Your Web Scrapers Keep Breaking (And How to Build Self-Healing TypeScript Agents Using LLMs and Playwright)
If you have ever maintained a production web scraping pipeline or an automated form-filling assistant, you know the sinking feeling of checking your l…
Adding passkey-backed human approval to high-risk MCP actions
AI agents are increasingly able to deploy code, modify infrastructure, query sensitive systems, and initiate financial operations. A conversational “A…
Stop Building Custom AI Integrations. Use MCP Instead.
AI agents are becoming part of everyday software. Customers want to ask ChatGPT to create tickets, update records, retrieve reports, trigger workflows…
My eval said a perfect MCP server was broken. It was the eval that was lying.
Originally published at tengli.dev When I added an LLM-powered eval to mcpgrade , the first real run produced a result that looked like a scoop: conte…
I Added an MCP Server to NPMScan for AI Coding Agents
I Added an MCP Server to NPMScan for AI Coding Agents AI coding agents are increasingly choosing libraries, installing dependencies, and modifying pac…
Beyond APIs: The Architecture of Autonomous "Computer Use" Agents in TypeScript
The architecture of modern artificial intelligence has reached a critical inflection point. For years, Large Language Models (LLMs) operated as isolat…
One Repo Became Three — Quietly, Then Publicl
One Repo Became Three — Quietly, Then Publicly ai #docker #security #mcp Previously Back in February, I published AI Sandbox Environment + DockMCP — a…
Building Custom MCP Clients in Next.js & Serverless Engines: The Ultimate Engineering Guide
The Model Context Protocol (MCP) has transformed how AI agents interact with local tools, filesystems, and databases. Originally built around a determ…
GitOps for AI Agents: Treating Tool Configs and Memory Like Production Infrastructure
GitOps for AI Agents: Treating Tool Configs and Memory Like Production Infrastructure Stop managing AI agent configurations as fragile scripts. Adopt …
Constraining the Agent: What I Learned Wiring MCP Into a Legacy System
Notes from January 2026, when giving an AI agent live database access still felt reckless. Written for engineers who are about to do this, and for the…
Stop Hardcoding AI Tools: Dynamic Tool Discovery and Schema Validation with Zod & MCP
If you are still hardcoding tool definitions, JSON schemas, and manual routing logic directly into your AI agent initialization scripts, you are build…
Mastering Node.js Transport Layers in MCP: Stdio vs. Server-Sent Events (SSE)
The Model Context Protocol (MCP) has completely transformed how modern Large Language Models (LLMs) and agentic runtimes discover, invoke, and interac…
What if MCP could manage your entire development runtime?
I created Agent-Up , an open-source desktop app and local server for running multiple coding-agent environments on one machine. Worktrees isolate sour…
Unlocking Atomic AI: How SKILL.md and the 5,776-Module Skill Registry are Engineering the Future of Developer Workflows
Unlocking Atomic AI: How SKILL.md and the 5,776-Module Skill Registry are Engineering the Future of Developer Workflows The TormentNexus Skill Registr…
Building Your First Model Context Protocol (MCP) Server with TypeScript and Zod
If you’ve been building AI agents or working with Large Language Models recently, you’ve likely hit the integration wall. Historically, connecting an …
Your coding agent knows your codebase. It knows nothing about your users.
Your AI agent can read every file in your repository. It knows your schema, your route handlers, the half-finished migration you left in alembic/versi…
Turning Claude into a Code Quality Auditor with MCP
Context switching is where engineering productivity goes to die. You're deep in a refactor inside Cursor or Claude Code, logic is flowing, and then—a …
Beyond CI/CD: GitOps for AI Agents - How to Version Control Your Agent's Memory and Roll Back Catastrophic Learning
Beyond CI/CD: GitOps for AI Agents - How to Version Control Your Agent's Memory and Roll Back Catastrophic Learning Discover how L2 Vault versioning i…
SQLite + Vector Search: The Dependency-Free AI Memory Stack
SQLite + Vector Search: The Dependency-Free AI Memory Stack Why are AI engineers moving from bloated vector databases to sqlite-vec? Discover how comb…
MCP Scorecard: 4-Layer Pre-flight Check Before You Publish a Server
The MCP ecosystem grew faster than the review rules for it. In the last few weeks I published three MCP servers of my own and each time I found myself…
How I reduced AI coding context by 95%
Every time I watched an AI coding assistant work on a large TypeScript project, I noticed the same pattern. It wanted to answer something simple like:…
How MCP Is Changing Website QA Workflows for Development Teams
Modern development teams use CI/CD pipelines, automated testing, feature flags, and AI-assisted coding to release new functionality multiple times per…
I lint-scanned 36 popular MCP servers. A third of them are failing your agent.
Originally published at tengli.dev Your MCP server can be 100% spec-compliant and still be unusable by an agent. The Model Context Protocol spec tells…
MCP vs. Agent Skills: A Decision Framework for Context Engineering
MCP vs. Agent Skills: What's the Difference and Which Do You Need? As AI agents evolve beyond basic chat interfaces into fully autonomous systems, dev…
Stop leaving your IDE to manage translations
I've spent a significant portion of my career dealing with the 'context switching tax.' You know exactly what I mean. You're deep in a flow state, ref…
How do you stop parallel coding agents from stomping on each other?
Our team of 3 runs a lot of coding agents in parallel on the same repo, often 10+ combined going at once (we love our subagents). Despite our small te…
MCP Session Architecture: Scale Agent Integrations Without Sticky Servers
AI agents rarely fail because the demo was bad. They fail when the same workflow must run for many users, across many tools, behind real load balancer…
Building an AI-Ready SaaS Discovery Engine with Next.js, PostgreSQL, and MCP
Software discovery used to be a straightforward search problem. A user typed a category, opened a few result pages, compared features, and selected a …
I built a local, keyless Firecrawl for Claude Code — here's why published: false
A language model pays for every token of nav, ads, and footer it reads. That one sentence is the whole reason tearsheet exists. I do a lot of research…