mzizi-mcp

Get design tokens

mzizi_get_tokens

Read-onlyIdempotent

The Mzizi brand system: 21 colour families (7 minerals, 7 heritage, 7 experimental), semantic colours, typography, spacing, radii and the ecosystem brands, and the Bundu floor: the minimums nothing can go under (17px body, 14px captions, 49px hit region, 7:1 body contrast, and the spacing floor (14px inset, 7px gaps between controls, 7px between a label and its field, 7px between items, 1.5 body leading)). Ask for floors for the floor in one call (the spacing floor is also under accessibility), and for colors to get every colour family in one call. For text, use each family's textLight / textDark on the base surface, and onContainerLight / onContainerDark on its container; never use hex, lightHex or darkHex as a text colour (they are accents).

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "mzizi_get_tokens"
  }
}

Input Schema

Name	Required	Description	Default
`family`	No	One of: colors (all 21 colour families at once), floors (the Bundu floor: sizes, contrast and the spacing floor, with how it is enforced), minerals, heritage, experimental, semantic, backgrounds, typography, spacing (the scale, plus the spacing floor), radii, ecosystem, componentSpecs, accessibility, voiceAndTone, philosophy. Common aliases resolve (status/semanticColors, radius, type/fonts, exp, floor/bundu-floor/spacing-floor). Omit for everything.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedNov 4, 2026

changedInput schema / properties / family / description

Previous value: -"One of: colors (all 21 colour families at once), minerals, heritage, experimental, semantic, backgrounds, typography, spacing, radii, ecosystem, componentSpecs, accessibility, voiceAndTone, philosophy. Common aliases resolve (status/semanticColors, radius, type/fonts, exp). Omit for everything."New value: +"One of: colors (all 21 colour families at once), floors (the Bundu floor: sizes, contrast and the spacing floor, with how it is enforced), minerals, heritage, experimental, semantic, backgrounds, typography, spacing (the scale, plus the spacing floor), radii, ecosystem, componentSpecs, accessibility, voiceAndTone, philosophy. Common aliases resolve (status/semanticColors, radius, type/fonts, exp, floor/bundu-floor/spacing-floor). Omit for everything."

Changed2 schema fields changedNov 1, 2026

changedInput schema / $schema

Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"

addedInput schema / properties / family / maxLength
```
Added value: +100
```

First observedSep 30, 2026

TDQS

A3.7/5.0

Behavior4/5

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

Annotations already declare readOnly/idempotent/non-destructive, so the bar is lower, and the description still adds domain behavior: aliases resolve, omitting the family returns everything, and hex/lightHex/darkHex are accents not text colours, with the correct textLight/textDark/onContainer fields named. That last rule materially changes how the agent uses the output.

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

Conciseness4/5

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

It is dense but informative, and the escape hatches (floors, colors) are called out early. It does bloat slightly by restating the spacing floor twice and front-loading a catalogue of contents before stating the action, which costs a little front-loading quality.

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

Completeness4/5

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

With one optional parameter, full schema coverage, annotations, and no output schema, the definition covers what the content is and how to cite it. The one real gap is scale: 'Omit for everything' gives no sense of how large the full payload is, so an agent cannot judge whether to scope the call.

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 coverage is 100% and the schema's family description already lists every value and alias, so the description's repetition of floors/colors adds little on that axis. The genuine addition is the text-versus-accent colour semantics, but that concerns output rather than the parameter itself, so the 3 baseline holds.

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

Purpose4/5

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

The description enumerates exactly what the tool serves up: 21 colour families, semantic colours, typography, spacing, radii, ecosystem brands, and the Bundu floor. The implicit verb is 'return', never stated outright, but the resource is unmistakable and clearly distinct from siblings like mzizi_get_component and mzizi_search.

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

Usage Guidelines3/5

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

It gives query-level routing advice ('ask for `floors` for the floor in one call', '`colors` for every family in one call') and rules for consuming the results, which is real guidance. It never says when to use this tool versus mzizi_check_accessibility or mzizi_get_component, and gives no exclusions, so sibling selection is left to inference.

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

All mzizi-mcp tools Inspect

Try in Browser

Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?