Skip to main content
Glama
design-system-mcp
by dgesteves

List design-system components

list_components
Read-onlyIdempotent

Lists every design-system component with its native element, variants, parts, and import so agents can write matching UI; call before writing UI and filter by query, kind, or limit.

Instructions

List every component in the project design system with a one-line description, the native element it renders, its variant values, its parts and its import. Icons (components that render an ) are named on one line per import, or per folder for icons with a module each, five or more to a line. Call this before writing UI in this project. query, kind and limit narrow a long list. At a monorepo root, pass path for the project of the file you are editing; without it, every project is listed, each component with its package.

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": "list_components"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindNo"icon": only the components that render an <svg>, one by one. "component": all the others.
pathNoIn a monorepo served from its root: the file you are editing, or a project folder, relative to the root, to answer from that project. Without it, every project is listed together. Ignored in a single project. When the server was started outside your project, pass the file as an absolute path: the project is found from it.
limitNoMost components to list one by one.
queryNoOnly components with this text in their name, their parts' names or their description.

Output Schema

NameRequiredDescriptionDefault
iconsNoWithout `kind`: icons, the components that render an <svg>, by name, five or more per module, or per folder for icons with a module each.
omittedNoMatching components left out by `limit`.
componentsYesThe components listed one by one, after `query`, `kind` and `limit`.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed10 schema fields changedv0.12.1
    • addedInput schema / properties / kind
      Added value: +{
      +  "description": "\"icon\": only the components that render an <svg>, one by one. \"component\": all the others.",
      +  "enum": [
      +    "component",
      +    "icon"
      +  ],
      +  "type": "string"
      +}
    • addedInput schema / properties / limit
      Added value: +{
      +  "description": "Most components to list one by one.",
      +  "maximum": 1000,
      +  "minimum": 1,
      +  "type": "integer"
      +}
    • changedInput schema / properties / path / description
      Previous value: -"In a monorepo served from its root: the file you are editing, or a project folder, relative to the root, to answer from that project. Without it, every project is listed together. Ignored in a single project."New value: +"In a monorepo served from its root: the file you are editing, or a project folder, relative to the root, to answer from that project. Without it, every project is listed together. Ignored in a single project. When the server was started outside your project, pass the file as an absolute path: the project is found from it."
    • addedInput schema / properties / query
      Added value: +{
      +  "description": "Only components with this text in their name, their parts' names or their description.",
      +  "maxLength": 1000,
      +  "type": "string"
      +}
    • addedOutput schema / properties / components / description
      Added value: +"The components listed one by one, after `query`, `kind` and `limit`."
    • addedOutput schema / properties / components / items / properties / subcomponents / description
      Added value: +"Left out when none."
    • addedOutput schema / properties / components / items / properties / variants / description
      Added value: +"Left out when none."
    • changedOutput schema / properties / components / items / required
      Previous value: -[
      -  "name",
      -  "importPath",
      -  "variants",
      -  "subcomponents"
      -]New value: +[
      +  "name",
      +  "importPath"
      +]
    • addedOutput schema / properties / icons
      Added value: +{
      +  "description": "Without `kind`: icons, the components that render an <svg>, by name, five or more per module, or per folder for icons with a module each.",
      +  "items": {
      +    "additionalProperties": false,
      +    "properties": {
      +      "from": {
      +        "description": "The module they are imported from, or, with `modules`, the folder of their modules.",
      +        "type": "string"
      +      },
      +      "modules": {
      +        "description": "For icons with a module each: each one's module, in the order of `names`.",
      +        "items": {
      +          "type": "string"
      +        },
      +        "type": "array"
      +      },
      +      "names": {
      +        "items": {
      +          "type": "string"
      +        },
      +        "type": "array"
      +      },
      +      "package": {
      +        "description": "At a workspace root: the package its source belongs to, e.g. \"@acme/ui\".",
      +        "type": "string"
      +      }
      +    },
      +    "required": [
      +      "from",
      +      "names"
      +    ],
      +    "type": "object"
      +  },
      +  "type": "array"
      +}
    • addedOutput schema / properties / omitted
      Added value: +{
      +  "description": "Matching components left out by `limit`.",
      +  "type": "integer"
      +}
  2. First observedv0.6.0

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered; the description still adds real context beyond that. It discloses output-shaping behavior the agent could not otherwise predict — icons collapsed to one line per import or per folder, five or more to a line — and a non-obvious edge case: `path` is ignored in a single project and cross-project listing occurs when it is omitted. It does not discuss result size caps or pagination beyond `limit`, which is the remaining gap.

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?

The purpose and the 'call this before writing UI' directive are front-loaded, which is good. But the icon sentence ('named on one line per import, or per folder for icons with a module each, five or more to a line') is dense and hard to parse on a first read, mixing two different collapse rules into one clause. The overall length is reasonable, yet that sentence is the least clear use of words in an otherwise efficient description.

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?

Return values need not be explained since an output schema exists, and annotations cover the safety profile, so the description's job is mainly usage and edge-case framing — both are present, including monorepo project selection and icon truncation. For a zero-required-parameter listing tool, that is close to sufficient; only explicit sibling routing is missing.

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 each of the four parameters is already documented in detail, including the enum split and the monorepo/absolute-path rule. The description adds only a light framing ('`query`, `kind` and `limit` narrow a long list') plus a restatement of the `path` behavior already in the schema. Baseline 3 applies because the schema carries the semantic load.

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 opening sentence gives a specific verb and resource ('List every component in the project design system') and enumerates exactly what each entry carries: description, native element, variant values, parts, import. That is far more informative than a restatement of the name. It stops short of explicitly distinguishing itself from the siblings get_component and search_components, leaving the agent to infer the list-vs-get-vs-search split from the names alone.

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?

'Call this before writing UI in this project' gives a clear triggering condition, and the note that `query`, `kind` and `limit` narrow a long list tells the agent how to use the tool rather than abandon it on large corpora. The monorepo guidance ('pass `path` for the project of the file you are editing; without it, every project is listed') gives another concrete usage rule. What's absent is explicit routing: it never says when a caller should prefer search_components or get_component instead.

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