Skip to main content
Glama
EricSeokgon

egovframe-scaffold-mcp

by EricSeokgon
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

공통컴포넌트 제거

remove_egovframe_components
Destructive

Delete installed eGovFrame components by removing only manifest-recorded files, rejecting dependencies or modified files by default, with backup and dry-run options.

Instructions

add_egovframe_components로 조립한 컴포넌트를 제거합니다. 설치 매니페스트에 기록된 파일만 삭제하며, 다른 설치 컴포넌트가 의존하거나 설치 시점 hash와 달라진 파일은 기본 거부합니다. force=true는 remove-backup/에 사본을 만든 뒤 트랜잭션 제거하며, dryRun 미리보기를 지원합니다.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
forceNo사용자 수정·hash 미검증 파일도 remove-backup/에 백업한 뒤 제거
dryRunNotrue면 삭제 없이 대상만 미리보기
componentsYes제거할 컴포넌트 id 목록
projectDirYes대상 프로젝트 디렉터리

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.21.0
    • addedInput schema / properties / force
      Added value: +{
+  "default": false,
+  "description": "사용자 수정·hash 미검증 파일도 remove-backup/에 백업한 뒤 제거",
+  "type": "boolean"
+}
  2. Addedv0.19.0

TDQS

A4.7/5.0
Behavior5/5

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

Annotations already declare destructiveHint=true and readOnlyHint=false, yet the description adds substantial behavior beyond them: deletion is manifest-scoped only, files with dependents or changed hashes are rejected by default, force makes a backup in remove-backup/ before transactional removal, and dryRun previews targets. This is exactly the mutation-specific context an agent needs before a destructive call.

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?

Three tightly packed sentences, front-loaded with purpose then the default safety policy then the force preview behavior. No filler and every clause carries operational weight.

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

Completeness5/5

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

For a destructive, non-idempotent mutation tool with a fully documented 4-parameter schema and no output schema, the description covers scope, default rejection rules, override semantics, backup location, and preview support. Nothing an agent needs to call it safely is missing.

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?

Schema coverage is already 100%, so baseline is 3. The description adds meaning beyond the schema by framing force as a backup-then-transactional-remove and tying dryRun to a non-destructive preview, and adds the concept of transactional removal that the schema does not state.

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?

Names a specific verb+resource (제거 / remove components) and ties it directly to the counterpart operation ('add_egovframe_components로 조립한 컴포넌트를 제거합니다'), so an agent immediately understands this is the inverse of the add tool. No other sibling performs removal, so it is clearly differentiated.

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 scopes usage to components assembled via add_egovframe_components and explains the default rejection policy (dependencies, hash mismatch), which tells the agent when a plain call will fail and when force is needed. It stops short of explicit when-not guidance or naming a non-removal alternative, but the operational context is clear.

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

Deploy Server

Other Tools