hello.new

Publish a website

publish_site

Publish a website you built (HTML, CSS, JavaScript, images) at an address of its own that anyone can visit. Give people the url; keep id and key to change it with update_site. Static files only: no server code runs, and everything in the site is public. Expires in 24 hours unless the user connected a hello.new account.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "files": "<files>"
    },
    "name": "publish_site"
  }
}

Input Schema

Name	Required	Description
`files`	Yes	Every file of the site. index.html is the home page; pages link to the rest by path, like "style.css". At most 100 files and 10 MB.
`title`	No	What the site is, for the user's dashboard.
`expires_in`	No	Seconds until the link expires. Default: 24 hours, or never on a hello.new account.

Output Schema

Name	Required	Description
`id`	Yes
`key`	Yes	For the other tools. Never give it out.
`url`	Yes	The link. Give it to people.
`claim_url`	No	Anonymous links: where the user can keep the link past 24 hours.
`stats_url`	Yes	A live dashboard of who opened the link, for the user.
`expires_at`	Yes	null: it never expires.

Schema Changelog

Changes observed during successful MCP inspections.

AddedOct 3, 2026

TDQS

A4.5/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the annotations (openWorld, not read-only, not destructive), it discloses genuinely new traits: everything published is public, no server code runs, the link expires in 24 hours unless a hello.new account is connected, and the returned id/key are needed for future updates. These are exactly the consequences an agent needs before acting.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three tight sentences, front-loaded with what the tool does, then the credential handoff, then the constraints. Every clause carries information; nothing is padding.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present, return values need not be explained, and the description covers everything else an agent needs: static-only constraint, public exposure, expiry behavior, and the alternative tool for edits.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so files/title/expires_in are already fully documented in the schema, including the index.html convention and 100-file/10MB limits. The description mirrors the expiry default rather than adding new parameter meaning, so the baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific verb (publish) and resource (a website built from HTML/CSS/JS/images) served at its own public URL. It distinguishes itself from the sibling update_site by explaining that id and key are kept specifically to change the site later.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives clear context for use (a static site the user built that others should visit) and routes modification to update_site. It does not state when *not* to use it, e.g. when a dynamic/server-backed app is needed, though the 'static files only' line partly covers this.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All hello.new tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?