Your agent/Cursor

Deploy without leaving the editor.

Cursor already has the project open and the agent that wrote it. Add agenthost and the deploy stops being the bit you tab away to do.

Everything else is in here. Why is the deploy somewhere else?

You edit here, you run here, you fix the failing test here. Then shipping it means a browser tab, an account, a project wizard and a set of questions about build commands, and the flow you were in is gone.

agenthost puts that step back where the rest of the work is. Cursor’s agent gets tools it can call, so “deploy this” is a thing it does with the project already in front of it. There is no build command to declare and no framework to pick, which is what makes it possible for the agent to finish the job rather than turn round and ask you something.

The loop closes too. When the deployed version misbehaves, Cursor can read the running app’s logs, jump to the file, change it and deploy again. When the change was a mistake, the previous version goes back.

You ask for it in a sentence.

There are no commands to learn on our side. These are whole sentences, typed the way you would say them to a person, and each one is a thing agenthost does.

deploy this

Sends the open project, works out the runtime from the files, and answers with a working https link.

hook it up to the github repo instead

Links the repo and deploys from a branch, so a push and a deploy stop being two chores.

it's crashing on boot, look

Reads the logs of the running app, finds the error, and gets to fix it in the same turn.

give the client a preview link, but private

Publishes it and locks it to the addresses you name, so it is a real link rather than a screen share.

undo that deploy

Puts the previous version back at the same address.

There is more of this in the how-to guides, which are written for your agent to read as much as for you.

Whatever it built, it can publish.

You do not have to know what it is made of. Your agent works that out and tells us.

  • framework preset
  • build command
  • output directory
  • install command
  • API keys
  • credit card
  • region

Nothing here can stop and ask you a question.

Every one of these is a setting some other host would demand before it would take your files. None of them exists here, which is why your agent can go from a folder to a working link without checking in.

  • Dockerfiles
  • port settings
  • TLS certificates
  • DNS records
  • CI pipelines
  • health checks
  • scaling rules

The one thing agenthost does expect is an entrypoint per runtime, and the deploy reference is where Cursor reads it before the first deploy.

How it connects.

The button hands Cursor the server details and opens its install prompt. Nothing is added until you approve it.

Add agenthost to Cursor ↗

By hand: Settings → MCP → Add new global MCP server, with the address https://agenthost.eu/mcp.

1

Add the server

Cursor shows you what it is about to install, with the name and the address. You approve it, and it is added globally rather than per project.

2

Sign in with your email

The first time the agent calls agenthost it opens your browser. You type the code we email you and approve the connection. There is no key field.

3

Ask for a link

Say deploy this. If you are new to agenthost, that same first deploy is what creates your account.

Nothing is added until you approve it, and Cursor never handles a password. The get started page walks through all of it, with the buttons and the sign-in step.

The usual ones.

Does the project have to be in git?

No. Cursor sends the files from the folder you have open. If the project does live on GitHub you can link the repo and deploy from a branch instead, but that is a choice rather than a requirement.

Deploying from a GitHub repo →

Is it added per project or for everything?

The button adds it globally, so agenthost is there in every workspace you open. You can add it to a single project instead from Cursor's MCP settings if you would rather keep it scoped.

Can it deploy a monorepo, or just the root?

Tell it which folder is the thing you want online and it sends that. agenthost looks at what is inside the folder it is given, so an app in a subdirectory deploys the same as one at the root.

What can it do besides deploy?

Create projects, read logs, roll back, attach a database, set environment variables, add a domain, invite people to something private, and open a support ticket if it gets stuck.

The full tool reference →

Is there an API key to paste anywhere?

No. agenthost signs you in through your browser, and your agent never sees a password or a key. There is nothing to copy out of one window and into another, and nothing to rotate later.

What does it cost to try?

Nothing, and there is no card. Your first ten websites are free and stay free. You only pay when the thing you built has to run code on our side, or when you want it on your own domain.

What it costs →

Can I connect more than one agent to the same account?

Yes, as many as you like. They all see the same projects, so you can build something in one and update it from another. Connecting the second one is a single click, because your browser is already signed in.

Where is this actually hosted?

In the EU, by a European company. Your files, your database and your logs stay here, and so does the billing.

Not what you use?

agenthost is a standard remote MCP server, so anything that speaks MCP can drive it. These are the ones with a page of their own.

Point Cursor at it.

One button to connect, no card, and shipping stops being the part you leave the editor for.