hoaster

Your agent can build almost anything — a landing page, an infographic, an interactive HTML page, an image.

CommunityOnlineNo sign-inGlobalFreeCan modify data

What it can do

  • Publish: Publishes content to the public internet and returns a real URL that anyone can open. Reach for this whenever the user wants to put something online, share it on the web, or get a public link
  • List Spaces: Lists the spaces belonging to the authenticated user. Each space has: `name` — the user-facing label, show this to the user; `slug` — the globally-unique handle used in published URLs, wh

What data it sees

Do you need an account

No: the server works without sign-in

Your agent can build almost anything — a landing page, an infographic, an interactive HTML page, an image. Hoaster is the last mile: over MCP, your agent publishes that artifact to a clean, public URL you own, optionally on your own custom domain. Connect once with a browser sign-in (OAuth 2.1 — no tokens to copy-paste), then it's one sentence forever: "publish it." Built for makers, consultants, and marketers who want their work to live on their URL, not inside someone else's chat product.

How to connect

How to connect hoaster to Claude

The server address to paste into Claude settings:

https://hoaster--hoaster.run.tools

  1. Open Claude (claude.ai or the desktop app).
  2. Go to Settings → Connectors.
  3. Click Add custom connector.
  4. Paste the server address copied below into Remote MCP server URL and click Add.
  5. In a chat, click + → Connectors and switch the new connector on.

Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.

Authorization

After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.

How to connect hoaster to ChatGPT

The server address to paste into ChatGPT settings:

https://hoaster--hoaster.run.tools

  1. Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
  2. Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
  3. Open Settings → Connectors and click Create.
  4. Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
  5. Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
  6. In a new chat open + → Apps/Connectors and enable the connector.

OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.

Authorization

On first use ChatGPT opens the service's sign-in window. Sign in and approve access.

How to connect hoaster to Cursor

The server address to paste into Cursor settings:

https://hoaster--hoaster.run.tools

Fastest: click Open in Cursor below and confirm the prompt.

Manually:

  1. In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
  2. Paste the JSON copied below into ~/.cursor/mcp.json (per project: .cursor/mcp.json in the repo root).
  3. Save the file. The server appears in the MCP list; authorize it there if asked.

Authorization

If the service needs sign-in, an authorize button appears next to the server in the MCP list.

Server tool list (2)

Raw names from tools/list. Only developers need these.

publishPublishes content to the public internet and returns a real URL that anyone can open. Reach for this whenever the user wants to put something online, share it on the web, or get a public link for what was just created — even if they never mention Hoaster by name. Accepts any web content — an HTML page, image, SVG, JSON, CSS, JS, plain text, … — addressed by a short URL slug; set `contentType` to match what you're posting. Re-publishing the same slug updates that page in place. `spaceId` is optional: omit it to publish into your space when you have exactly one. If you have none or several, the call fails WITHOUT publishing anything (so it's harmless) and tells you what to do. Recommended flow: call publish without a spaceId first; if it fails, call `list_spaces`, show the spaces to the user to choose one, then call publish again with that space's id.
list_spacesLists the spaces belonging to the authenticated user. Each space has: `name` — the user-facing label, show this to the user; `slug` — the globally-unique handle used in published URLs, which may also be worth showing; `id` — an internal identifier to pass as `spaceId` to the `publish` tool, which should generally NOT be shown to the user.