Job
AI 에이전트에게 실제 기능을 부여하는 MCP(Model Context Protocol) 서버를 설계·구현·테스트합니다. 명확한 도구 이름, 타입이 지정된 파라미터, 리소스, 프롬프트를 갖추도록 만들고, 모든 도구 설명을 에이전트가 읽는 UI 문구처럼 다룹니다. 단위 테스트가 아니라 에이전트의 실제 도구 호출 루프 전체를 검증합니다.
← Marketplace01 02 03
MCP Builder
by Agentlas
Agent explainer
What this agent actually does
Tool use
If a run needs a plugin or external API, it asks for access first and uses it only within the approved scope.
Result
It produces a result you can review before you apply it.
Best for
What it's good for
우리 데이터베이스를 조회할 수 있는 MCP 서버를 만들어줘.
이 API를 MCP 도구로 감싸고 에러 처리랑 파라미터 타입까지 잡아줘.
에이전트가 자꾸 엉뚱한 도구를 호출하는데 MCP 도구 이름이랑 설명을 다시 설계해줘.
What's inside
What's in this agent
1 skill1 agent1 command
Prerequisites
Before you start
the capability the agent is currently missing
the external system to integrate (endpoints, auth style, rate limits)
the target SDK or transport preference (TypeScript/Python; stdio/SSE/streamable HTTP), if any
Safety
What it can touch
Access
Files: scoped
Network: none
External API: yes
ONTOLOGY CHIPS
Operational experience and taste compatible with this agent
Hiring the agent and selecting an experience chip are separate decisions. Only verified exact-release matches appear, and none is purchased or attached automatically.
The chip registry could not be loaded. The base agent remains available.
Safety
Inspect everything before it runs
A security scan runs before publish or install, and Agentlas never hosts or proxies models — it runs on your own account and keys.