Skip to main content
Glama
enesjakozh
MatthewDailey

MCP Starter Server

by MatthewDailey
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

MCP 스타터 서버

AI 어시스턴트 도구를 구축하기 위한 최소 ModelContextProtocol 서버 템플릿입니다. 이 스타터는 Claude와 같은 AI 어시스턴트와 함께 사용할 수 있는 MCP 도구를 만드는 데 필요한 기본 구조를 제공합니다.

특징

  • 간단한 "hello world" 도구 예제

  • TypeScript + esbuild 설정

  • 미리 구성된 개발 도구

Related MCP server: MCP Server Scaffold

Claude를 사용하여 빌드하고 실행하기 위한 설정

  1. claude.ai/download 에서 Claude 데스크톱 앱을 다운로드하고 설치하세요.

  2. 저장소를 복제하고 종속성을 설치하고 빌드합니다.

지엑스피1

  1. Claude가 이 MCP 서버를 사용하도록 구성하세요. MCP 서버를 처음 사용하는 경우 이 프로젝트의 루트에서 다음을 실행하세요.

echo '{
  "mcpServers": {
    "mcp-starter": {
      "command": "node",
      "args": ["'$PWD'/dist/index.cjs"]
    }
  }
}' > ~/Library/Application\ Support/Claude/claude_desktop_config.json

이렇게 하면 claude_desktop_config.json 에 다음과 같은 항목이 생성됩니다.

"mcpServers": {
  "mcp-starter": {
    "command": "node",
    "args": ["/Users/matt/code/mcp-starter/dist/index.cjs"]
  }
}

기존 MCP 서버가 있는 경우 기존 설정에 mcp-starter 블록을 추가하세요. args <path_to_repo_on_your_machine>/mcp-starter/dist/index.cjs 경로라는 점이 중요합니다.

  1. Claude Desktop을 다시 시작합니다.

  2. 서버가 실행 중인지 확인하려면 Claude의 인터페이스에서 사용 가능한 도구의 수가 표시된 망치 아이콘을 찾으세요.

  3. 이 모든 것이 제대로 작동한다면 npm run dev 사용하여 MCP 서버를 개발하고 Claude에서 테스트할 수 있습니다. MCP 서버를 다시 시작할 때마다 Claude를 다시 시작해야 합니다.

Inspector를 사용하여 개발

개발 및 디버깅 목적으로 MCP Inspector 도구를 사용할 수 있습니다. Inspector는 MCP 서버 상호 작용을 테스트하고 모니터링할 수 있는 시각적 인터페이스를 제공합니다.

자세한 설정 지침은 Inspector 설명서를 참조하세요.

Inspector를 사용하여 로컬로 테스트하려면:

npm run inspect

파일 변경 사항을 적용하려면 다음을 실행하세요.

npm run watch

또는 watcher와 inspector를 모두 실행합니다.

npm run dev

출판

서버를 배포할 준비가 되면 간단합니다!

  1. NPM 계정을 설정합니다.

  2. npm publish 실행하세요. package.json 에 있는 프로젝트 이름을 사용하여 패키지를 게시합니다.

  3. 게시된 후 다른 사용자는 다음과 같은 구성 항목으로 서버를 설치할 수 있습니다.

"mcpServers": {
  "<your-package-name>": {
    "command": "npx",
    "args": ["<your-package-name>"]
  }
}

사용 가능한 도구

서버는 다음을 제공합니다.

  • hello_tool : 이름 매개변수를 받아서 인사말을 반환하는 간단한 예제 도구

새로운 도구 만들기

새로운 도구를 추가하려면:

  1. index.ts 에 도구 스키마를 정의합니다.

  2. ListToolsRequestSchema 핸들러의 도구 배열에 추가합니다.

  3. CallToolRequestSchema 핸들러에 구현을 추가합니다.

hello_tool 구현을 예로 들어 보겠습니다.

Available Tools

1 tool
hello_toolD

Hello tool

ParametersJSON Schema
NameRequiredDescriptionDefault
nameYesThe name of the person to greet

TDQS

D1.7/5.0
Behavior1/5

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. 'Hello tool' discloses nothing about side effects, return values, or operational behavior, leaving the agent completely uninformed beyond the tool's name.

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

Conciseness2/5

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

The description is extremely short, but this is under-specification rather than effective conciseness. It is a two-word tautology that provides no informative structure or front-loaded value.

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

Completeness2/5

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

While the tool is simple and the schema fully documents its one parameter, the description still fails to state the tool's purpose or expected behavior. An agent may infer from the name and parameter that it greets a person, but the description itself is incomplete.

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 only parameter, 'name', is described as 'The name of the person to greet'. This meets the baseline where the schema does the heavy lifting. The description itself adds no additional parameter meaning.

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

Purpose1/5

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

The description 'Hello tool' simply restates the tool name without a verb, resource, or outcome. It does not specify that the tool greets a person or what action it performs, and it fails to distinguish itself from siblings like plan_trip or search_location.

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?

The description provides no guidance on when to use this tool or when to prefer an alternative. There are no exclusions, conditions, or context clues to help an agent decide between hello_tool and its siblings.

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. 1 tool updatev1.0.0
    • First observedhello_tool
Deploy Server
Shareable, User-Owned Context BackendPeople, applications, and agents read, write, and coordinate together in one context lake. Reach it over MCP, a CLI, a Python SDK, or REST.fulcradynamics.comAd

TDQS

C2.2/5.0

Scored across 1 tool

Disambiguation5/5

With only one tool, there is no possibility of ambiguity or overlap between tools, making it perfectly clear which tool to use for any task within this server's scope.

Naming Consistency5/5

The single tool name 'hello_tool' follows a consistent verb_noun pattern, and with no other tools to compare, there is no inconsistency in naming conventions.

Tool Count2/5

One tool is generally too few for a server's purpose unless it is extremely trivial, which 'hello_tool' suggests. This feels thin and under-scoped for a typical MCP server, indicating a mismatch in tool count appropriateness.

Completeness1/5

With only a 'hello_tool', the server lacks any meaningful coverage of a domain. It is severely incomplete, as there are no operations for CRUD, lifecycle management, or any substantive workflows, making it inadequate for agent-driven tasks.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

  • MCP Server Scaffold

    vjouenne76
    F
    license
    B
    quality
    D
    maintenance
    A basic starter project for building Model Context Protocol (MCP) servers that enables standardized interactions between AI systems and various data sources through secure, controlled tool implementations.
    2
    -

  • Hello World MCP FastAPI

    bankszach
    F
    license
    Not graded
    quality
    D
    maintenance
    A minimal Model Context Protocol server built with FastAPI that provides a basic "Hello World" resource and tool. Serves as a starting point for building and validating MCP client integrations with richer resources and tools.
    -

  • mcp-base

    sesopenko
    A
    license
    Not graded
    quality
    D
    maintenance
    A bare-bones FastMCP server template designed to serve as a starting point for building custom Model Context Protocol servers. It provides a foundational structure for implementing tools over HTTP and includes a built-in health check utility.
    GPL 3.0

Appeared in Searches