Claude Code builds it.
Now let it ship it.
You are already in the terminal, in the project, with the thing that wrote it. Putting it online should not mean opening a browser and filling in a form. It should mean saying so.
Claude Code can do the whole job. Except the last bit.
It reads the codebase, writes the feature, runs the tests and fixes what it broke. Then it stops, because deploying means a dashboard, and a dashboard means you. So the session ends with a folder on your laptop and a job on your list.
agenthost closes that gap. It is a set of tools Claude Code can actually call, so the deploy is one more thing it does rather than one more thing it hands back to you. There is no build command to declare and no framework to pick, which matters more than it sounds: those are the questions that would otherwise send it back to ask you something you would have to go and look up.
It also means the loop closes. When a deploy comes up wrong, Claude Code can read the logs, see the stack trace, change the file and deploy again without you relaying anything between two windows. When the fix is worse than the bug, it can put the old version 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.
put this online
Uploads what you have, works out the runtime from the files, and answers with a working https link. No project to create first.
it's 500ing, look at the logs
Reads the running app’s logs itself, finds the stack trace, and gets to change the code and redeploy in the same turn.
point studiofern.com at it
Adds the domain and tells you the one record to paste at your registrar. The certificate is handled here.
put the previous version back
Every deploy keeps the one before it, so a rollback is a sentence rather than an incident.
give me a token so CI can deploy this
Mints a long-lived API token for the runs that cannot open a browser. Deploying from CI →
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.
A website or page
The one-pager, the portfolio, the event invite. Files, served fast, with nothing to build first.
Ten free, forever, no card.
How it works →An app that saves things
Sign-ups, notes, bookings, orders. Somewhere to run and a database to remember, together.
€4 a month, database included.
How it works →Node, Python, PHP
Express, Flask, Django, a script that has to run. One fixed convention each, and no build command to get right.
The contract, in full.
What runs here →- 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 Claude Code reads it before the first deploy.
How it connects.
One command, once. -s user makes agenthost available in every project rather than only the one you are standing in.
claude mcp add --transport http agenthost https://agenthost.eu/mcp -s user
Run the command
It writes agenthost into your Claude Code config and does nothing else. No key, no account needed yet.
Sign in with your email
Run /mcp inside Claude Code and pick agenthost. Your browser opens, you type the code we email you, and you approve it by name.
Ask for a link
Say put this online. If you are new to agenthost, that same first deploy is what creates your account.
Nothing is added until you approve it, and Claude Code 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 my project have to be in git?
No. Claude Code sends the files it has, straight from the folder you are working in. If you do keep the project on GitHub, you can link the repo instead and deploy from a branch, but nothing here requires it.
What if Claude Code is running somewhere without a browser?
Sign in once as yourself on a machine that has one, then ask for an API token and give that to the headless run. Tokens are long-lived and sent as a bearer header, which is what CI, cron jobs and unattended agents use.
Can it deploy something it did not write?
Yes. agenthost cares about what is in the folder, not where it came from. An old project, something you exported from another tool, a site a colleague sent you as a zip: point Claude Code at it and ask.
What can it actually do once it is connected?
Create projects, deploy, read logs, roll back, attach a database, set environment variables, add a domain, invite people to a private app, and open a support ticket if it gets stuck. It is the same set of tools whichever client you connect from.
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.
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.
Claude
The Claude apps and claude.ai. Claude builds you something, then gives you the link to it.
Read more →Claude Cowork
Cowork works away on the thing for an hour, then publishes it at a real address.
Read more →ChatGPT
Turn on developer mode, paste one address, and ChatGPT can put things online.
Read more →Codex
The Codex CLI, app and IDE extension, all from the one config file they share.
Read more →Gemini
Gemini CLI in the terminal, and custom apps in the Gemini web app.
Read more →Microsoft 365 Copilot Cowork
A plugin your admin uploads once, with the deploy skill built in.
Read more →Cursor
One button, and Cursor can publish what it just built for you.
Read more →VS Code
GitHub Copilot's agent mode, with agenthost added as an MCP server.
Read more →Point Claude Code at it.
One command to connect, no card to add, and the first link takes about a minute.