はじめにGet started · Publish with Claude

Get started

Publish with Claude

Ask Claude for a prototype, a report, a dashboard or a small site, and Kazari gives it an address on your organisation’s domain. You do not need a repository, a build step or a hosting account. This guide is for anyone who works with Claude, whether you write code or not.

You need an Kazari instance. Your administrator will give you its address, which looks like art.example.com in the examples below. If you are the administrator, start with Install.

Connect Claude#

claude.ai#

Add Kazari as a custom connector:

1. In claude.ai, open Settings → Connectors and add a custom connector.
2. Enter the address https://mcp.art.example.com/ (your instance’s mcp. address) and connect.
3. Claude.ai sends you to sign in. If your organisation has set up single sign-on, use your work account; otherwise Kazari asks for an API key, which your administrator can issue for you.
4. Kazari shows a consent page naming claude.ai, your account and what it may do. Approve it once.

On Team and Enterprise plans, an owner may need to add the connector for the organisation before members can connect it.

Claude Code#

claude mcp add --transport http kazari https://mcp.art.example.com/

The first time Claude Code uses the server it opens your browser to sign in, exactly as above. To use an API key instead, add --header "Authorization: Bearer kzk_..." to the command.

Kazari’s repository also ships a Claude Code skill with its conventions and recipes. Install it for all your projects with:

mkdir -p ~/.claude/skills/kazari
curl -fsSL https://raw.githubusercontent.com/PeterBooker/kazari/main/skills/kazari/SKILL.md \
  -o ~/.claude/skills/kazari/SKILL.md

Other MCP clients#

Any client that speaks MCP over Streamable HTTP can connect to https://mcp.art.example.com/, either by signing in through OAuth or with an Authorization: Bearer kzk_... header. Many clients take a JSON entry along these lines; check your client’s documentation for where it goes:

{
  "mcpServers": {
    "kazari": {
      "url": "https://mcp.art.example.com/",
      "headers": { "Authorization": "Bearer kzk_..." }
    }
  }
}

Ask for a page#

Say what you want and that it should go on Kazari. Naming a slug is optional, but it decides the address and cannot be changed later.

Claude always replies with the address, for example Published https://signup-flow.art.example.com/ (version 1).

Versions and addresses#

Every publish creates a new version, and old versions are never changed or thrown away:

• https://signup-flow.art.example.com/ shows the published version, usually the newest.
• https://signup-flow--v2.art.example.com/ shows version 2, always.

Share the main address with people who should see the latest work. Put a version address in feedback, sign-off or a ticket when it matters exactly what someone looked at.

Share safely#

• Public pages appear in the listings that other Kazari users see. Unlisted pages are left out of other people’s listings but are still open to anyone with the link.
• Unpublished takes a page offline at once (visitors get “not found”) without deleting anything. Ask Claude to make it public or unlisted again to bring it back.
• Search engines are told not to index pages unless you ask for the page to be indexable.

Tidy up#

Pages you no longer need can retire themselves. Ask Claude to mark a page stale with a grace period (“retire it in two weeks”). The page keeps working until the grace period ends, then:

1. it is soft-deleted: offline, but it can be restored for 30 days (by default; ask your administrator);
2. it is purged: the files are gone, and old links say “gone” for 90 days;
3. the slug is freed and can be used again.

Changed your mind during the grace period? Ask Claude to unmark it, or publish a new version, which clears the mark too. Deleting a page outright is possible too; Claude should check with you before a permanent delete.

What works in a page#

Kazari serves static files: HTML, CSS, JavaScript, images, fonts and data files. Claude knows these rules from the tool descriptions, but they help when you ask for something ambitious:

• One index.html is enough. It is served at the root address. Extra files (styles, scripts, images, JSON data) are fine, and links between them should be relative (about.html, not /about.html) so they also work on version addresses.
• Libraries from the common CDNs work. By default scripts may load from cdnjs, jsDelivr and unpkg, styles from Google Fonts, and images from any https address. Other sources are blocked by the browser.
• Data travels with the page. A page can fetch its own files, such as data.json, but not other websites or APIs. Put the data in the page or next to it.
• No server-side code. There is nowhere to run PHP, an API route or a database, and forms cannot save anything on the server. For a prototype, fake the behaviour in JavaScript.
• Each page is its own site. localStorage and cookies are private to the page, so a prototype can remember state without seeing anyone else’s.
• Single-page apps that route in the browser need a setting so that every path serves index.html: ask Claude to set the metadata kazari.spa to true.
• Size. By default a version can hold up to 50 MiB and 2,000 files, and one file up to 25 MiB. Above about 2 MiB, Claude is told to send files in chunks, so large pages work too.

Your instance’s limits and allowed sources may differ; the tool descriptions Claude sees always state the real ones.

When something goes wrong#