MMA MCP Server
This MCP server provides access to South Korea's Military Manpower Administration (병무청) database to search for companies designated for alternative military service programs.
Core Functionality:
Search for companies eligible for alternative military service: Industrial Technical Personnel (산업기능요원), Specialized Research Personnel (전문연구요원), and Ship Service Reserve (승선근무예비역)
Search Filters:
Service type (required) - Select from three alternative military service categories
Company name - Search for specific companies
Industry sectors - Filter across 32+ sectors including IT, electronics, manufacturing, construction, mining, transportation, energy, and fisheries
Location - Filter by province (시/도) and district (시/군/구)
Company size - Filter by enterprise category (large enterprise/대기업, SME/중소기업, mid-sized/중견기업, other/기타)
Hiring status - Show only companies with active recruitment postings
Position availability - Filter by military service quotas (TO) for active duty (현역) or supplementary service (보충역)
Output:
Returns up to 30 company records per query in CSV format with headers
Includes company name, industry sector, location, and position availability information
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@MMA MCP Serversearch for industrial technician positions in Seoul Gangnam-gu"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MMA MCP Server
병무청 병역일터(Military Manpower Administration) API를 위한 Model Context Protocol (MCP) 서버입니다.
기능
이 MCP 서버는 병무청 병역일터에서 병역특례 지정업체 정보를 조회할 수 있는 도구를 제공합니다.
search_designated_entities
병역특례 업체 검색 및 조회 기능을 제공합니다.
파라미터:
필수 파라미터
eopjong_gbcd(string): 복무 형태 선택 (필수)'산업기능요원'- 산업기능요원'전문연구요원'- 전문연구요원'승선근무예비역'- 승선근무예비역
선택 파라미터
al_eopjong_gbcd(array): 업종 그룹 코드 리스트예:
['정보처리', '게임SW', '전자']
eopjong_gbcd_list(array): 업종 선택 목록업종 코드 배열
gegyumo_cd(string): 기업 규모''- 전체 (기본값)'대기업'- 대기업'중소기업'- 중소기업'중견기업'- 중견기업'농어민후계'- 농어민 후계자'기타'- 기타
eopjong_cd(string | array): 업종 코드단일 값 또는 배열로 전달 가능
예:
'정보처리'또는['정보처리', '전자']
eopche_nm(string): 회사 이름특정 회사명으로 검색
빈 값은 전체 조회
sido_addr(string): 시/도 선택예:
'서울특별시','경기도','부산광역시'등
sigungu_addr(string): 시/군/구 주소sido_addr의 하위 지역
예:
'강남구','수원시'등빈 값은 해당 시/도 전체 조회
chaeyongym(string): 병무청 채용 공고 등록 업체 여부''- 전체 (기본값)'Y'- 채용 공고 등록 업체만
bjinwonym(string | array): TO 유무'H'- 현역 TO 있음'B'- 보충역 TO 있음['H', 'B']- 현역/보충역 모두 조회
반환값:
CSV 형식의 검색 결과 (헤더 포함)
최대 30개의 업체 정보
각 행은 업체명, 업종, 위치, TO 정보 등을 포함
사용 예시:
// 산업기능요원 - 정보처리 업종 - 서울 강남구
{
"eopjong_gbcd": "산업기능요원",
"eopjong_cd": "정보처리",
"sido_addr": "서울특별시",
"sigungu_addr": "강남구"
}
// 전문연구요원 - 중소기업 - 채용공고 있음
{
"eopjong_gbcd": "전문연구요원",
"gegyumo_cd": "중소기업",
"chaeyongym": "Y"
}
// 특정 회사명 검색
{
"eopjong_gbcd": "산업기능요원",
"eopche_nm": "네이버"
}Related MCP server: job-search-mcp
업종 코드 목록
제조업 (Manufacturing)
철강, 기계, 전기, 전자, 화학, 섬유, 신발
시멘요업, 생활용품, 통신기기
정보처리, 게임SW, 영상게임
의료의약, 식음료
농산물가공, 수산물가공, 임산물가공, 동물약품
애니메이션
광업 (Mining)
석탄채굴, 일반광물채굴, 선광제련
에너지 (Energy)
에너지
건설업 (Construction)
국내건설, 국외건설
운수업 (Transportation)
내항화물, 외항화물, 내항선박관리, 외항선박관리
수산업 (Fisheries)
근해, 원양
CI/CD
이 프로젝트는 GitHub Actions를 사용하여 자동화된 CI/CD 파이프라인을 제공합니다.
자동화 워크플로우
CI (Continuous Integration):
main,develop브랜치에 push하거나 PR 생성 시 자동으로 린트, 테스트, 빌드를 실행합니다.Release:
v*.*.*형식의 태그를 push하면 자동으로 GitHub Release를 생성하고 빌드 결과물을 첨부합니다.CodeQL: 보안 취약점 자동 분석 (매주 월요일 + PR/Push 시)
Dependabot: 의존성 자동 업데이트 제안 (매주)
릴리즈 생성 방법
# 버전 태그 생성 및 푸시
git tag v1.0.0
git push origin v1.0.0자세한 내용은 .github/workflows/README.md를 참조하세요.
설치
pnpm install빌드
pnpm build실행
pnpm start개발 모드
pnpm dev테스트
pnpm testMCP 클라이언트 설정
Claude Desktop 또는 다른 MCP 클라이언트에서 이 서버를 사용하려면, 설정 파일에 다음을 추가하세요:
Claude Desktop 설정
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
Linux: ~/.config/Claude/claude_desktop_config.json
{
"mcpServers": {
"mma": {
"command": "node",
"args": ["/path/to/agent-for-agent/dist/index.js"]
}
}
}프로젝트 구조
agent-for-agent/
├── src/
│ ├── index.ts # MCP 서버 메인 엔트리포인트
│ ├── mma-api.ts # MMA API 클라이언트 함수
│ ├── types.ts # TypeScript 타입 정의
│ └── __tests__/
│ └── mma-api.test.ts # 테스트 코드
├── dist/ # 빌드 결과물 (TypeScript 컴파일 후)
├── package.json
├── tsconfig.json
├── jest.config.js
└── README.md기술 스택
Runtime: Node.js 18+
Language: TypeScript 5.x
Framework: MCP SDK (@modelcontextprotocol/sdk)
HTTP Client: Native Fetch API
Excel Parser: xlsx (SheetJS)
Validation: Zod
Testing: Jest + ts-jest
Code Quality: ESLint, Prettier
Package Manager: pnpm
개발 가이드
타입 시스템
이 프로젝트는 TypeScript의 strict mode를 사용하며, 모든 타입이 types.ts에 정의되어 있습니다.
API 클라이언트
mma-api.ts는 병무청 API와 통신하는 로직을 포함합니다:
Form data 생성 및 인코딩
HTTP 요청 처리
Excel 파일 파싱 및 CSV 변환
에러 핸들링
테스트
테스트는 Jest를 사용하며, fetch API를 모킹하여 실제 네트워크 요청 없이 테스트합니다.
# 전체 테스트 실행
pnpm test
# Watch 모드로 테스트
pnpm test:watch코드 품질
# Linting
pnpm lint
# Formatting
pnpm format라이선스
MIT
주의사항
이 서버는 병무청 병역일터의 공개 API를 사용합니다. API 사용 시 해당 사이트의 이용 약관을 준수해야 합니다.
기여
버그 리포트나 기능 제안은 이슈로 등록해주세요.
참고 자료
Available Tools
1 toolsearch_designated_entitiesA
병무청 병역일터에서 병역특례 지정업체를 검색합니다. 산업기능요원, 전문연구요원, 승선근무예비역 복무가 가능한 업체 정보를 조회할 수 있습니다. 검색 결과는 CSV 형식으로 반환되며, 최대 30개의 업체 정보가 제공됩니다.
| Name | Required | Description | Default |
|---|---|---|---|
| service_type | Yes | (필수) 복무 형태를 선택합니다. | |
| company_size | No | 기업 규모 (선택사항, 빈 값은 전체 조회) | |
| industry_sectors | No | 업종 코드 (선택사항, 여러 개 가능) | |
| company_name | No | 회사 이름 (선택사항, 빈 값은 전체 조회) | |
| city_province | No | 시/도 선택 (선택사항, 빈 값은 전국 전체 조회) | |
| city_district | No | 시/군/구 주소 (선택사항, 빈 값은 city_province 전체 조회) | |
| is_hiring | No | 병무청 채용 공고 등록 업체 여부 (선택사항, 'Y' 또는 빈 값) | |
| military_service_status | No | 현역 또는 보충역 TO 유무 (전체 조회시 H, B 모두 입력) |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It effectively describes key behavioral traits: it specifies the output format (CSV), result limit (maximum 30 companies), and that it's a read-only search operation (implied by '검색합니다' and '조회할 수 있습니다'). However, it doesn't mention potential rate limits, authentication requirements, or error conditions.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is appropriately concise with three sentences that each serve a clear purpose: stating the tool's function, specifying the types of companies searched, and describing output format and limits. It's front-loaded with the core functionality, though the second sentence could be slightly more streamlined.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's moderate complexity (8 parameters, no output schema, no annotations), the description provides good contextual completeness. It covers the tool's purpose, scope, output format, and result limits. The main gap is the lack of output schema, but the description compensates by specifying CSV format and maximum result count, though it doesn't detail the CSV structure.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema description coverage is 100%, so the schema already documents all 8 parameters thoroughly with descriptions and enums. The description doesn't add any parameter-specific information beyond what's in the schema, maintaining the baseline score of 3 where the schema does the heavy lifting without additional value from the description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose with specific verbs ('검색합니다', '조회할 수 있습니다') and resources ('병역일터', '병역특례 지정업체'), specifying the exact data source and target entities. It distinguishes the tool by mentioning the three specific military service types it supports, making its scope explicit even without siblings.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage context by stating what types of companies can be searched (those supporting specific military service types), but it doesn't provide explicit guidance on when to use this tool versus alternatives. Since no sibling tools are listed, there's no opportunity for comparison, but it lacks information about prerequisites or typical use cases beyond the basic functionality.
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. Dates show when Glama detected each change.
1 tool update
- First observed
search_designated_entities
TDQS
With only one tool, there is no possibility of ambiguity or overlap between tools. The tool 'search_designated_entities' has a single, clear purpose focused on searching for designated entities related to military service exemptions.
The tool name 'search_designated_entities' follows a consistent verb_noun pattern (search + designated_entities). Since there is only one tool, there are no inconsistencies or deviations to evaluate, making it perfectly consistent.
A single tool is too few for a server that appears to cover military service exemption entities, as it lacks basic operations like creating, updating, or deleting entities, and may not support comprehensive workflows. This feels thin and incomplete for the apparent scope.
The tool set is severely incomplete for the domain of military service exemption entities. While the search tool exists, there are obvious gaps such as no CRUD operations (e.g., create, update, delete entities), no detailed entity retrieval, or other lifecycle management tools, which will likely cause agent failures in broader tasks.
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
Korean business registry, corporate info, parcel tracking, validation APIs
Search company disclosures and financial statements from the Korean market. Retrieve stock profile…
Search job postings, companies, and technology stacks across 10M+ companies.
Search and compare SaaS built in South Korea. 3,800+ services, liveness-checked weekly.
Related MCP Servers
- FlicenseAqualityBmaintenanceEnables searching corporate disclosures from Korea's DART system, including company info, financial statements, and disclosure search.16-
- AlicenseAqualityCmaintenanceSearches job postings from Korean job platforms (JobKorea, Saramin) by company name, offering both single and bulk search tools.21022MIT
- FlicenseNot gradedqualityDmaintenanceEnables searching for French companies using the official data.gouv.fr API, with filters for name, location, activity, and certifications.1-
- FlicenseAqualityCmaintenanceEnables searching and filtering public institution job postings from the Korean government's ALIO system via MCP.2-
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/antegral/agent-for-agent'
If you have feedback or need assistance with the MCP directory API, please join our Discord server