Think inside your AI world.
How do I connect Cloudflare to ChatGPT?
Cloudflare's managed remotes serve any MCP client — account config, Workers bindings, builds and docs, readable from ChatGPT.
Direct answer: connect Cloudflare's managed remote MCP servers to ChatGPT. In ChatGPT, add it from the connector settings (developer mode); the tool's own docs carry the current path. Authorised, ChatGPT reads account configuration, Workers bindings, builds and documentation — the edge estate as it actually is, not as remembered.
Config truth, on demand
Which rules are live, where the Worker's bindings point, how the last build went — read from the account. The gap between believed config and actual config is where edge incidents breed; reads close it.
DNS changes keep office hours
Worked case: you ratified a DNS window — zone changes land Tuesday or Wednesday mornings only, with the afternoon watched, after a Friday-evening record change once turned into a weekend of cache-poisoned confusion. Cloudflare applies changes any hour you like; that some hours are yours and some are the weekend's is scheduling law you wrote.
Through Unl the change conversation arrives scheduled: DNS edit proposed on a Thursday afternoon — outside your window, the poisoned-weekend story standing. The law holds because it is present, not because someone remembered Friday's ghost.
Cloudflare to ChatGPT reads the edge estate; through Unl the estate answers to the change windows you ratified — Friday's ghost votes at every DNS conversation.
Reads through Unl arrive with measured context — in the presence of the decisions you’ve already settled. The reach lane is live: 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.
Read further
Questions people ask
What do the managed remotes expose?
Account configuration, Workers bindings, builds and docs — observational, authorised per account, identical across clients.
Why a change window for DNS specifically?
Propagation makes DNS mistakes slow to see and slow to unwind — the worst shape for out-of-hours changes. A ratified window with its incident makes the discipline ambient.
Does Unl ever apply config?
Not while measuring — a read only reads, so checking a proposed change against your window rule never applies it. Past that the honest answer is that it can: where a server exposes a tool that writes, Unl can call it, and that call carries your explicit in-turn gesture, verified at the choke point, with anything not declared read-only treated as a write by default. Nothing lands as a side effect of a read — only when you ask and confirm.
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.