Skip to main content
Glama
deenesjakoptruzh
tabaldi98

bunge-ds-mcp

by tabaldi98
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

bunge-ds-mcp

@bunge/ds-components 디자인 시스템의 컴포넌트 카탈로그를 노출하는 MCP(Model Context Protocol) 서버입니다. AI 어시스턴트가 입력, 출력, 사용 예시 및 가져오기 지침을 포함한 컴포넌트의 전체 세부 정보를 나열, 검색 및 가져올 수 있도록 합니다.

이 서버는 stdio를 통해 통신하며(HTTP 포트를 노출하지 않음), MCP 클라이언트(예: VS Code Copilot)에 직접 통합되어 프로세스를 통해 통신합니다.

도구 (Tools)

도구

설명

list-components

카테고리별(form, layout, navigation, feedback, data-display, overlay) 선택적 필터링을 포함하여 사용 가능한 모든 컴포넌트를 나열합니다.

get-component

ID별로 컴포넌트의 전체 세부 정보(입력, 출력, 사용법, 가져오기)를 반환합니다.

search-components

이름, 설명 또는 태그로 컴포넌트를 검색합니다.

get-component-usage

컴포넌트의 사용 예시와 가져오기 지침을 반환합니다.

시작하기

사전 요구 사항

  • Node.js 18+

  • npm 9+

설치 및 빌드

npm install
npm run build

로컬 실행

npm start

서버는 stdio를 통해 시작되며 HTTP 포트는 없습니다. 프로세스에 직접 연결되는 MCP 클라이언트에 의해 사용됩니다.

MCP 클라이언트 설정 (예: VS Code)

{
  "mcpServers": {
    "bunge-ds-mcp": {
      "command": "npx",
      "args": ["bunge-ds-mcp"]
    }
  }
}

또는 로컬 빌드를 가리키는 경우:

{
  "mcpServers": {
    "bunge-ds-mcp": {
      "command": "node",
      "args": ["dist/index.js"]
    }
  }
}

package.json 스크립트

스크립트

명령어

설명

build

tsc

TypeScript를 dist/ 폴더의 JavaScript로 컴파일합니다.

start

node dist/index.js

MCP 서버를 시작합니다(사전 빌드 필요).

dev

tsc --watch

watch 모드에서 컴파일하며 변경 시 자동으로 다시 컴파일합니다.

dev:inspect

tsc && npx @modelcontextprotocol/inspector node dist/index.js

컴파일 후 MCP Inspector를 열어 도구를 대화형으로 테스트합니다.

test

vitest run

단위 테스트를 한 번 실행합니다.

test:watch

vitest

watch 모드에서 테스트를 실행합니다.

docker:infra:up

docker compose up -d --wait

4873 포트에서 Verdaccio(비공개 npm 레지스트리)를 실행합니다.

docker:infra:down

docker compose down

Verdaccio 컨테이너를 중지하고 제거합니다.

registry:login:private

npm login --registry http://localhost:4873

로컬 비공개 레지스트리(Verdaccio)에 로그인합니다.

release:private

npm version patch && npm publish --registry http://localhost:4873

버전을 증분(patch)하고 로컬 비공개 레지스트리에 게시합니다.

로컬 인프라 (Docker)

docker-compose.yaml은 4873 포트(http://localhost:4873)에서 Verdaccio(비공개 npm 레지스트리)를 실행합니다. 공개 npm에 게시하지 않고 패키지 게시를 시뮬레이션하는 데 사용됩니다.

npm run docker:infra:up    # sobe o Verdaccio
npm run registry:login:private  # autentica no registry local
npm run release:private    # publica o pacote localmente

프로젝트 구조

src/
├── index.ts              # Entrada: cria o McpServer e conecta ao transport
├── tools/                # Registro das tools (uma por arquivo)
│   ├── index.ts          # Barrel — registra todas as tools
│   ├── list-components.ts
│   ├── get-component.ts
│   ├── search-components.ts
│   └── get-component-usage.ts
├── data/
│   └── components.ts     # Catálogo de componentes do DS
├── models/
│   └── mcp-server.model.ts  # Interfaces e tipos
└── tests/
    ├── data.spec.ts
    └── tools.spec.ts

Available Tools

4 tools
get-componentA

Retorna detalhes completos de um componente: inputs, outputs, exemplos de uso e import.

ParametersJSON Schema
NameRequiredDescriptionDefault
idYesID do componente (ex: "button", "list")

TDQS

A3.6/5.0
Behavior2/5

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

No annotations provided, so description must disclose behavior. It only states what is returned, but does not mention potential errors, authentication, rate limits, or side effects. For a read operation, basic behavioral transparency is missing.

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

Conciseness5/5

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

The description is a single sentence that efficiently conveys the tool's purpose and return value. It is front-loaded with the key action and resource.

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?

Given no output schema, the description adequately lists the types of details returned (inputs, outputs, usage examples, import). Missing error handling or scope details, but sufficient for a simple fetch tool.

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?

The input schema has 100% description coverage for the single parameter 'id'. The description does not add meaning beyond the schema example. Baseline 3 is appropriate as schema covers the parameter.

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

Purpose5/5

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

The description clearly states the verb 'retorna' and the resource 'detalhes completos de um componente', specifying the content: inputs, outputs, usage examples, and import. It distinguishes from sibling tools like list-components and search-components.

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?

The description implies use for fetching full details of a specific component, but lacks explicit guidance on when to use versus alternatives or when not to use. No exclusions or prerequisites are mentioned.

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

get-component-usageB

Retorna exemplos de uso e instruções de import de um componente.

ParametersJSON Schema
NameRequiredDescriptionDefault
idYesID do componente (ex: "button", "list")

TDQS

B3.3/5.0
Behavior2/5

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

No annotations are provided. The description only states what it returns, but does not disclose any behavioral traits such as whether it is safe, requires authentication, or has side effects.

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

Conciseness5/5

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

A single, concise sentence that efficiently communicates the tool's purpose with no extraneous information.

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?

The description is adequate for a simple tool with one parameter, but lacks details about the return format or structure of the usage examples and import instructions. Could be more complete given there is no output schema.

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% (the 'id' parameter has a clear description in the schema). The tool description adds no additional meaning beyond the schema, earning the baseline score of 3.

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

Purpose5/5

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

The description clearly states it returns usage examples and import instructions for a component (specific verb and resource). It distinguishes from siblings like 'get-component' (which likely returns component details), 'list-components', and 'search-components'.

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?

No guidance on when to use this tool versus alternatives. It does not provide any context about prerequisites, scenarios, or exclusions.

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

list-componentsA

Lista todos os componentes disponíveis no Design System, com filtro opcional por categoria.

ParametersJSON Schema
NameRequiredDescriptionDefault
categoryNoFiltrar componentes por categoria

TDQS

A3.7/5.0
Behavior3/5

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

No annotations are provided, so the description carries full burden. It discloses basic behavior (list components, filter) but does not mention return format, pagination, or potential side effects.

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

Conciseness5/5

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

The description is a single concise sentence that front-loads the purpose and includes the optional filter, with no unnecessary words.

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 simple list tool with one optional parameter and no output schema, the description is minimally adequate but does not describe return value structure or other contextual details.

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?

The description restates the category filter already documented in the schema, adding no extra meaning beyond what the schema provides. Schema coverage is 100%.

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

Purpose5/5

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

The description clearly states the tool lists all available components in the Design System with an optional category filter, distinguishing it from sibling tools like get-component (single component) and search-components (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?

The description implies use for listing with optional filtering but does not explicitly contrast with siblings or provide when-not-to-use guidance.

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

search-componentsA

Busca componentes por nome, descrição ou tags.

ParametersJSON Schema
NameRequiredDescriptionDefault
queryYesTermo de busca para encontrar componentes

TDQS

A3.8/5.0
Behavior2/5

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

No annotations are provided, so the description must disclose behavioral traits. It only states the search fields (name, description, tags) but omits details like case sensitivity, partial matching, pagination, or read-only nature. This is insufficient for a search tool.

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?

The description is a single, front-loaded sentence that conveys the core purpose. It is appropriately sized for a simple tool with one parameter, though it could include brief behavioral notes.

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?

Given no output schema and simple parameters, the description is minimally adequate but lacks details on return format, pagination, or matching behavior. It covers the essential 'what' but not the 'how' of results.

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?

The schema covers the single parameter with a description ('search term'), and the description adds value by specifying the fields searched (name, description, tags). This extra context helps the agent understand what the query matches against.

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

Purpose5/5

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

The description clearly states the action (search) and the resource (components) with the scope (by name, description, or tags). It distinguishes from sibling tools like list-components (which lists all) and get-component (single component retrieval).

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?

The description implies usage context: use this tool when searching components by specific terms. While it does not explicitly mention alternatives, the sibling tool names (list-components, get-component) naturally differentiate the use cases.

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

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 4 tool updatesv1.0.2
    • First observedget-component
    • First observedget-component-usage
    • First observedlist-components
    • First observedsearch-components
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A3.9/5.0

Scored across 4 tools

Disambiguation4/5

The tools have distinct purposes, but get-component-usage is a subset of get-component, potentially causing minor confusion. Descriptions help differentiate, so overall good.

Naming Consistency5/5

All tools follow a consistent verb_noun snake_case pattern (get-, list-, search-), making them predictable and easy to understand.

Tool Count5/5

With 4 tools, the set is well-scoped for browsing a design system, covering listing, searching, and retrieving details without being excessive.

Completeness5/5

The tools provide full coverage for component browsing: list with filter, search, full details, and usage info. No obvious gaps in this domain.

Resources

Related MCP Connectors