Candor UI docs

Candor UI's design system

get_design

Read-onlyIdempotent

The design system as Markdown: every colour role and what it's for, the type scale, radius, shadows, motion, density and themes, read from the shipped CSS; how an app re-tokens for its brand; and how to build the screens around Candor components (surfaces, rhythm, writing, do and don't).

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": "get_design"
  }
}

Input Schema

Name	Required	Description	Default
`version`	No	A release, e.g. "2.6.2": the page as that release published it, for a project that has that version installed. Default: the version the server's URL passes (`?kit=`, which `npx candor-ui mcp` writes from candor-lock.json), else the current docs. When that release's docs weren't kept, or the page isn't in them, the answer is the current page with a note saying so.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedNov 10, 2026

addedInput schema / properties / version

Added value: +{
+  "description": "A release, e.g. \"2.6.2\": the page as that release published it, for a project that has that version installed. Default: the version the server's URL passes (`?kit=`, which `npx candor-ui mcp` writes from candor-lock.json), else the current docs. When that release's docs weren't kept, or the page isn't in them, the answer is the current page with a note saying so.",
+  "maxLength": 32,
+  "type": "string"
+}

First observedNov 8, 2026

TDQS

B3.2/5.0

Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint=false and destructiveHint=false, so the safety profile is fully covered by structured data. The description adds one genuinely useful behavioral fact — the content is "read from the shipped CSS," making it authoritative rather than editorial — but says nothing about output size, pagination, or how large the Markdown payload is.

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

Conciseness3/5

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

It is a single sentence, front-loaded with the core identity, and every clause corresponds to real content. However, the semicolon-chained enumeration of a dozen topics makes it dense and hard to scan, with no structure to separate tokens from guidance.

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

Completeness3/5

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

For a read-only, zero-required-param documentation fetch with no output schema, the content inventory is adequate and the version semantics live in the schema. The gap is that an agent cannot judge the payload's size or cost before calling, and no alternative tool is referenced for narrower needs.

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

Parameters4/5

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

Schema description coverage is 100% and the single `version` parameter is documented in unusual depth, including the default resolution chain via `?kit=` and the fallback to current docs with a note. The description contributes nothing about `version`, so its role is purely schema-carried; baseline 3 would apply, but the schema's thoroughness makes the combined definition stronger.

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 names the exact resource ("The design system as Markdown") and enumerates its contents — colour roles, type scale, radius, shadows, motion, density, themes, re-tokenizing, and screen-building guidance — so an agent can predict what comes back. It lacks an explicit verb ("returns"/"read") and never distinguishes itself from near siblings like get_component_docs or get_pattern.

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

Usage Guidelines2/5

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

There is no when-to-use or when-not-to-use guidance, and no named alternative. The agent must infer that this is the token/foundation source while get_component_docs covers individual components, which is guesswork rather than stated routing.

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

All Candor UI docs 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.