Think inside your AI world.
Cloudflare through Unl
Cloudflare shows the configuration in full. Whether it matches the security baseline you decided is your call — and config drifts quietly.
Cloudflare through Unl reads your live setup — account config, Workers bindings, builds, docs — against the security baseline you have ratified, so drift comes back flagged with the baseline rule it breaks.
What Cloudflare holds
Cloudflare’s managed remote MCP servers expose the platform surface:
- Account configuration
- Workers bindings
- Builds and documentation
What the naked read gives you
A naked read returns the current config. Accurate, and it won’t flag that a new binding is publicly reachable, because “no public bindings without review” is your baseline, not a Cloudflare default it enforces on you.
The frame judges the data it is given; it does not verify the source’s accuracy.
What changes when Cloudflare is read measured
Say you’ve ratified a security baseline: no publicly reachable Workers bindings without review, and rate-limiting on every public route.
“Does the config hold to our baseline?” returns, measured: no — a new binding is public without a recorded review, and one route has rate-limiting off, both breaching the baseline you set to keep the surface tight. Cloudflare supplied the config; your ratified baseline supplied the checks and the reasons.
And back again
When you approve the public binding for a documented reason and record it, the next config read treats it as reviewed rather than drift.
The answer comes back measured against what you already decided, and why.
The lane is live and open to this tool today: one box, paste anything. If it speaks MCP, Unl can reach it. Readings arrive unprompted, the data beside the criterion; Unl is a courier, not a warehouse, and keeps only your keys and the frame.
Questions people ask
Can AI check my Cloudflare config against a security baseline?
Yes, through Unl. You ratify the baseline (no unreviewed public bindings, required protections, with reasons), and the live config is measured against it — drift is flagged with the rule it breaks.
How do I connect Cloudflare to Claude?
Cloudflare offers managed remote MCP servers over account config, Workers and builds. Through Unl the same config arrives measured against your ratified baseline, so it reads as holds-or-drifted.
Does Unl change my Cloudflare setup?
Unl reads through Cloudflare, and can write back on your explicit gesture — it never acts as a side effect of a read.
What this is
Think inside your AI world — you stay in command
Unlimitless (Unl to friends) holds what you've settled, reads what your tools are showing, and catches what's changed out in the world — and hands your AI whatever bears on the work, the moment it's needed, without you asking. The right thing, in front of the model, unprompted, with you in command of the call. So you keep moving toward what you set out to build, on top of everything you've already decided.
It plugs into Claude, Claude Code, ChatGPT and Cursor as an MCP connector. Quick to connect, in a couple of steps.
Unlimitless is open now to invited Alpha. Apply for the Beta waitlist to come in ahead of the full launch:
Alpha is invite-only · free at launch.