Curated · updated weekly

MCP Server Directory

The Model Context Protocol is how AI models reach your tools and data. These are the servers worth knowing — what each connects, who maintains it, how to run it. (New to MCP? Watch our explainer.)

Running an MCP server

Most reference servers run with a single command (npx @modelcontextprotocol/server-filesystem /path or a uvx/docker equivalent) and are wired into your client's MCP config (Claude Code/Desktop, IDEs, agent frameworks). Since the 2026 stateless revision you can also run them behind a standard load balancer — see Ep. 1 of the podcast.

⚠️ Ops note: an MCP server is an access grant. Scope filesystem roots, DB credentials and API tokens to exactly what the agent needs — treat every server like an IAM policy, not a convenience.

Missing a good one? It gets refreshed weekly with This Week in AIOps.

Get the field note by email

A short email when the calculators get new numbers, the directory gets new entries, and the week's episode lands. No hype — unsubscribe in one click.

Your address is used to send the field note and nothing else.

Who builds these tools

AIOps Field Notes is written by James Son, a network, security, and automation engineer, and everything here is tested in a live multi-vendor lab. That same lab work is behind two paid things for teams who run the infrastructure underneath the AI:

DriftWatch → Config-drift monitoring that explains what changed in plain English, with CIS/PCI checks. Read-only, never touches your gear. 14 days free, then from $29/mo. Config-drift & compliance audit → A one-time, flat-fee review of your network configs: what drifted, what is undocumented, and a CIS/PCI gap list — delivered as a client-ready report.