Skip to content
Kodza logo

Kodza MCP server

Which MCP servers are Kodza's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.

read 2026-10-28

← Back to Kodza

Whose server it is
  • Registry namedev.kodza/kodzaverified in the MCP registry

The registry name sits under kodza.dev. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

When we asked itchecked 2026-10-28
  • Stateanswerschecked 2026-10-28
  • Tools2
  • Server calls itselfkodza
  • Server version0.1.1
  • Protocol version2025-06-18

On 2026-10-28 the server answered initialize and tools/list without a sign-in. First answer in 163 ms.

Should an agent connect itNot proven either way yet
  • Whether its tools do the product's job has not been judged yet.
  • Checked on 5 of the 7 days it takes to judge reliability.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

Measured dailydaily checks: 5, the first on 2026-10-28
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 5 so far
  • Use407 npm downloads a week
  • Answeredmeasuring5 of the 7 daily checks it takes to print a share
  • Median first answer158 ms
  • Space in an agent's context≈ 445 tokensthe definitions of all its tools (2), which an agent carries on every turn
  • Tool definitionsA · 100 of 100
  • Typed results0 of 2 toolsdeclared outputSchema: results come typed, read once
  • Every tool passes all six checks.

What an agent can do with it

  • not sure · Drop animated buttons and links into a plain web page
  • not sure · Fetch a ready-made component into an existing project via AI
  • not sure · Add counters, progress bars and loaders without a build step

Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?

Worth a look

None of the five warning signs in these definitions.

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

Tools it offers2 tools · read 2026-10-28
  • search_components

    Find Kodza UI components (plain HTML/CSS/vanilla JS) by what they do or look like, e.g. "button fill hover", "image slider", "sticky header", "date picker". Leave query empty to list a whole category. Returns slugs to pass to get_component.

  • get_component

    The full code of one Kodza component (HTML, CSS and, when it has one, vanilla JS), its API (CSS variables with defaults, modifier classes, data attributes, events), what each key does when it takes the keyboard, its dark-mode values and…

How to connect

Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:

{
  "mcpServers": {
    "kodza": {
      "type": "http",
      "url": "https://kodza.dev/api/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http kodza https://kodza.dev/api/mcp

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://kodza.dev/api/mcp as a custom connector in the settings.

Also shipped through: npm

Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.