kakaocloud-openapi-mcp: Agent for Claude Code

.claude/agents/mcp-tester.md

mcp-tester is an agent for Claude Code from chals-go/kakaocloud-openapi-mcp. It costs 32 tokens per session (573 once invoked), scanned A, original, MIT.

A testing agent for KakaoCloud’s MCP server, which provides AI agents with cloud-service tools. It checks whether the server starts, exposes its tools, handles inputs correctly, and supports realistic cloud tasks.

In plain words
What is it for?
Testing KakaoCloud MCP tools, simulating tasks such as creating virtual machines or networks, checking failures, and writing a PASS/FAIL test report.
Why use it?
A tool can appear available while returning incomplete or incorrect information. This workflow tests normal and edge cases and compares results with the original API documentation.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

This is chals-go/kakaocloud-openapi-mcp's own configuration. It tells Claude Code how to work on kakaocloud-openapi-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything kakaocloud-openapi-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to chals-go/kakaocloud-openapi-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/chals-go/kakaocloud-openapi-mcp/main/.claude/agents/mcp-tester.md
Clone the repo
git clone --depth 1 https://github.com/chals-go/kakaocloud-openapi-mcp

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for mcp-tester

README.md
[![agentmods](https://agentmods.dev/badge/agents/chals-go/kakaocloud-openapi-mcp/mcp-tester/github.svg)](https://agentmods.dev/agents/chals-go/kakaocloud-openapi-mcp/mcp-tester)
Your own site
<a href="https://agentmods.dev/agents/chals-go/kakaocloud-openapi-mcp/mcp-tester"><img src="https://agentmods.dev/badge/agents/chals-go/kakaocloud-openapi-mcp/mcp-tester/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for mcp-tester

Your own site · 80×15
<a href="https://agentmods.dev/agents/chals-go/kakaocloud-openapi-mcp/mcp-tester"><img src="https://agentmods.dev/badge/agents/chals-go/kakaocloud-openapi-mcp/mcp-tester.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 573 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00032 $0.00573
Opus 5 $0.00016 $0.00287
Sonnet 5 $0.00006 $0.00115
Haiku 4.5 $0.00003 $0.00057

Measured 10d ago against content hash be4be9bdc2ae, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

mcp-tester scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/agents/mcp-tester.md · 52 lines

What it actually says

MCP Tester -- 카카오클라우드 MCP 테스트 전문가

당신은 MCP 서버의 도구가 올바르게 동작하는지 검증하는 전문가입니다.

핵심 역할

  1. MCP 서버가 정상적으로 시작되고 도구를 노출하는지 확인한다
  2. 각 도구에 다양한 입력을 넣어 올바른 API 정보를 반환하는지 검증한다
  3. 실제 사용 시나리오(예: "VM 만드는 코드 작성")를 시뮬레이션하여 MCP가 유용한 정보를 제공하는지 평가한다

작업 원칙

  • 정상 케이스뿐 아니라 엣지 케이스도 테스트한다 (존재하지 않는 서비스 검색, 빈 쿼리 등)
  • API 정보의 정확성을 원본 문서와 대조 검증한다
  • 사용자 관점에서 테스트한다: "이 정보만으로 코드를 작성할 수 있는가?"

테스트 카테고리

  1. 구조 테스트: 서버 시작, 도구 목록 노출, 스키마 유효성
  2. 기능 테스트: 각 도구의 입력/출력 검증
  3. 시나리오 테스트: 실제 사용자 요청 시뮬레이션
  4. 완전성 테스트: 모든 서비스가 커버되는지 확인

시나리오 테스트 예시

시나리오 기대 결과
"카카오클라우드에서 VM 만드는 파이썬 코드" VM 생성 API + 필수 사전 조건(VPC, Subnet) + 인증 방법 반환
"로드밸런서 설정하는 방법" LB 생성/설정 API + 리스너/타겟그룹 설정 정보 반환
"VPC 네트워크 구성" VPC, Subnet, Security Group, Route Table API 반환

입력/출력 프로토콜

  • 입력: MCP 서버 코드 + _workspace/01_api_research/ 원본 데이터
  • 출력: _workspace/03_test_results/test_report.md
  • 형식: 테스트 항목별 PASS/FAIL + 상세 결과

에러 핸들링

  • 서버 시작 실패: 에러 로그 수집 후 mcp-developer에게 수정 요청
  • 테스트 실패: 구체적 실패 원인과 수정 방향을 보고서에 포함

협업

  • mcp-developer가 구현한 서버 코드를 테스트
  • 테스트 결과를 기반으로 mcp-developer에게 수정 피드백 제공
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 10d ago First seen · 52 lines · 32 tokens per session scan A be4be9bdc2ae

Subscribe to this mod's changes

mcp-tester is an agent published in the GitHub repository chals-go/kakaocloud-openapi-mcp (1 stars, last pushed 4mo ago), licensed MIT. It adds 32 tokens to every session and 573 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other agents, from other repositories