MCP for agents

Sitebin speaks the Model Context Protocol, so Claude, ChatGPT and any other MCP client can publish a website and manage it afterwards — without you pasting files anywhere. It is the same API, the same permissions and the same quotas, reached over the protocol those clients already speak.

MCP is not a separate permission system. An agent can do exactly what a script holding the same credential can do: on app.sitebin.io that means an account API token, and a site created anonymously (a Drop) stays outside it, just as it stays outside the API. Self-hosted community instances have no accounts, so the endpoint is open there.

Connect

The endpoint is https://app.sitebin.io/mcp, streamable HTTP. Create an API token in the dashboard at /account first — it is what tells Sitebin which account the agent is publishing for.

Claude Code

claude mcp add --transport http sitebin \
  https://app.sitebin.io/mcp \
  --header "Authorization: Bearer $TOKEN"

Claude Desktop, ChatGPT and other clients

Anything that can add a remote MCP server takes the same URL and the same Authorization header. Clients that only speak stdio, or that cannot set a header, can bridge through mcp-remote:

npx mcp-remote https://app.sitebin.io/mcp \
  --header "Authorization: Bearer $TOKEN"

What the agent can do

Tool	What it does
`create_site`	Publish files as a new site. Returns the public URL, the edit id, and — once — the edit password.
`list_sites`	The sites your account owns. Needs a token.
`get_site`	Settings, usage and the file list.
`update_site`	Mode, entry file, view password, expiry, WebDAV/FTP, SPA fallback.
`list_files`	The site's files with their sizes.
`read_file`	One file's contents.
`write_files`	Add or overwrite files. With `replace`, the site ends up holding exactly what was passed.
`delete_file`	Remove one file.
`delete_site`	Remove the site and everything in it.
`add_domain`	Attach a custom domain. Enterprise.
`remove_domain`	Detach a custom domain.
`download_site`	The whole site as a zip.

How it behaves

With a token, every site the agent creates belongs to your account and gets your plan's quotas and lifetime. list_sites shows them, and the token replaces the edit password on all of them — so the agent never has to hold a per-site secret, and never has to ask you for one.

Without a token, an agent must pass a site's edit_password for every call, and on app.sitebin.io it cannot create sites at all. That is deliberate: anonymous publishing belongs on the drop page, in front of a person.

Files travel as JSON — {"path": "index.html", "text": "…"}, or base64 for images. One call carries up to 8 MiB; a bigger site belongs on WebDAV, FTP or the API's zip upload. Sites an agent created are recorded as such, which is how abuse gets traced if it ever happens.

A site is public. Anyone with the URL can read it, and an agent publishing on your behalf is publishing to the open web. Don't hand one credentials, private documents or personal data to put online, and remember that a page an agent wrote is a page you are hosting under your account.

Not yet: one-click connectors

Sitebin authenticates MCP with the same bearer tokens as the API, which every client that can set a header supports today. The connector directories at Anthropic and OpenAI additionally want OAuth 2.1 with dynamic client registration, so you could add Sitebin by clicking "connect" instead of pasting a token. That is designed and on the roadmap — it is not shipped, and this page will say so until it is.

Rate limits

The same ones the API has: site creation is limited per IP, and password attempts per IP and per site. An agent gets no more room than curl does.

← API Deploy from CI →