Skip to main content
Glama
gmlcjf0326

claude-code-hwp-mcp

by gmlcjf0326

hwp_form_workflow

Executes a multi-phase workflow for filling HWP form documents, including learning, planning, previewing, filling, and verifying, with support for field and table cell overrides.

Instructions

양식 파일 첨부 워크플로우. v0.7.5.4 read-only 기본: phase="all" 은 learn→plan→preview 에서 정지 (fill 은 사용자 명시 호출 필요). phase 별: learn(학습)→plan(계획)→preview(미리보기)→fill(명시)→verify(명시)→rollback(원본 복원). auto_fix 는 v0.7.5.4 부터 no-op (원본 서식 보호). table_cell_overrides/field_overrides 로 Claude host 가 직접 제어.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
phaseYes실행할 단계. "all" 은 read-only (learn→plan→preview 만)
form_fileNo양식 HWP/HWPX 파일 (learn 또는 all 첫 호출 시 필수)
session_idNo세션 ID (없으면 자동 생성)
output_pathNo저장 경로 (생략 시 form_file 옆에 _filled 접미사)
confirm_fillNofill 단계 진행 확인 (사용자 승인 완료)
user_requestNo사용자 요청 (plan 단계에서 estimate_workload 입력)
reference_fileNo참고 자료 (Excel/CSV/JSON/PDF/DOCX/HTML)
field_overridesNo필드명→값 직접 지정 (auto_map 결과 덮어쓰기)
auto_fix_enabledNov0.7.5.4: auto_fix 활성화 여부 (기본 false). true 여도 P0-2 runAutoFixLoop no-op 이므로 validate 만 수행.
auto_fix_thresholdNoauto_fix 점수 임계 (기본 85, auto_fix_enabled=true 일 때만 의미)
table_cell_overridesNo표 셀 직접 지정 (auto_map 결과 덮어쓰기)
auto_fix_max_iterationsNoauto_fix 최대 반복 (기본 2, auto_fix_enabled=true 일 때만 의미)
Behavior3/5

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

No annotations are provided, so the description carries the full burden. It discloses key behaviors: auto_fix is no-op since v0.7.5.4, table_cell_overrides/field_overrides allow direct control, and phases have specific stopping points. However, it lacks detail on file modification side effects, error handling, and permissions.

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

Conciseness4/5

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

The description is front-loaded with the main purpose and phase summary. It is somewhat verbose due to version details, but each sentence provides useful context. No wasted repetition.

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

Completeness4/5

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

Given the 12 parameters, nested objects, and lack of output schema, the description covers the workflow phases, auto_fix behavior, and override mechanisms comprehensively. It lacks return value description but otherwise provides sufficient context for an AI agent.

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 coverage is 100%, so the schema already documents parameters. The description adds some value by explaining phase behavior (e.g., 'all' is read-only) and auto_fix settings, but much of the description mirrors the schema descriptions.

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

Purpose4/5

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

The description clearly states it is a form file attachment workflow with specific phases (learn, plan, preview, fill, verify, rollback). It distinguishes itself by describing the phase structure and read-only default. However, it is somewhat technical and could be more concise for an AI agent.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explains when to use each phase (e.g., 'fill' requires explicit user call, 'all' is read-only) but does not explicitly compare to sibling tools like hwp_fill_fields or hwp_fill_table_cells. An agent might benefit from guidance on when to choose this workflow over other form-related tools.

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

Install Server

Other Tools

Latest Blog Posts

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/gmlcjf0326/claude-code-hwp-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server