Comprehensive Model Context Protocol server for managing Home Assistant through AI assistants.
Nothing to run from here
Workers' Compensation Application Helper (sanjae-apply) is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
99/100
trust score
5
tools declared
local
or remote
—
downloads a day
What it does
Korean workers' compensation claims: required KCOMWEL forms and articles; fills official PDF forms.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user workers-compensation-application-helper-sanja-mcp '--' npx -y sanjae-apply mcp
# 2 — ask your agent for something these tools do
# list_required_forms, get_form_catalog, fill_form and 2 more
Remote: OAuth sign-in · Package: no sign-in.
Workers' Compensation Application Helper (sanjae-apply) costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
SEAll 1 server
seojaehong1 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one can run either way — at an address its publisher runs, or as a process under your own user, with your files and your network — and this marketplace is in the path of neither.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user workers-compensation-application-helper-sanja-mcp '--' npx -y sanjae-apply mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Or connect to its publisher’s address
Its publisher also runs it at https://sanjae-apply.vercel.app/api/mcp/mcp: nothing to start on your machine, and this marketplace is not in the path.
claude mcp add --scope user --transport http workers-compensation-application-helper-sanja-mcp https://sanjae-apply.vercel.app/api/mcp/mcpFree on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it writes
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
What you approve
5 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Read from its source code. A server that builds its tool list when it starts can list more tools than this.
산재 보상 청구(요양·휴업·간병료이송비보조기·장해·유족·미지급·추가상병·재요양·본인부담치료비)에 필요한 서식(REQUIRED/CONDITIONAL/NOT_APPLICABLE)·첨부(PROVIDED/MISSING/SUBSTITUTABLE)·근거 조문·절차 안내·아직 답해야 할 질문을 돌려준다. 입력을 저장하지 않는다. READY_TO_SUBMIT 은 제출 가능이지 승인이 아니다.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| claim | string | yes | 급여 종류 |
| accidentKind | yes | 업무상 사고 / 출퇴근 / 질병 / 모름 | |
| thirdParty | yes | 가해자(제3자)가 있는가 | |
| treatmentEnded | yes | 해당 상병 치료가 이미 끝났는가 | |
| tags | array | no | 소음성 난청 · 척추/신경 · 관절 · 보조기 청구 |
| have | array | no | 이미 준비한 첨부 id (예: A_MEDICAL_RECORDS) |
근로복지공단 서식자료실에서 받은 서식 13종의 파일명·개정일·sha256·게시글 URL 과, 지금 채울 수 있는 서식(fillable)과 그 칸 이름(slots)·칸 설명(slot_labels, 서식 원문 글자)·도장 자리 이름(stamps). form_id 를 주면 그 서식만. fill_form 전에 이것으로 칸을 고른다.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| form_id | string | no | 예: F_YOYANG_APPLY |
form_id 의 공단 정본 서식에 값을 넣어 base64 로 돌려준다. format='pdf'(기본)는 정본 PDF 오버레이, format='hwpx'는 한글 문서(한글 2014+ 로 열어 고칠 수 있다). 먼저 get_form_catalog(form_id) 의 slot_labels 로 칸을 고른다(칸 이름은 두 형식이 같다). 서식의 선택지(사업주여부·친인척여부·근로자유형·신청 구분·예/아니오·개인정보 동의 등)는 해당 체크 칸에 true 를 넣어야 찍힌다. 아는 값은 빠짐없이 넣는다. 서버에 저장하지 않는다. 주민번호 등은…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| form_id | string | yes | 예: F_YOYANG_APPLY, F_HUYEOP_CLAIM … |
| values | object | yes | 칸 이름 → 값 |
| format | string | no | pdf(기본) 또는 hwpx(한글) |
| stamp | object | no | 도장. PDF·한글(hwpx) 출력 모두 신청인 서명란에 찍는다. 본인 또는 명의자 동의가 있는 이름만. 등록 인감 대용이 아니다(사용인감 성격) |
이름으로 성명인(원형·사각·타원) 또는 법인형(원주 법인명 + 중심 문자 + 하단 부문자) 도장 PNG(투명 배경)를 만들어 base64 로 돌려준다. 본인 또는 명의자 동의가 있는 이름만 쓴다. 등록 인감을 흉내 내는 용도가 아니다(사용인감 성격). fill_form 의 stamp.name 으로 바로 찍을 수도 있다.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| name | string | no | 성명인 이름(2~4자). 동봉 글꼴(나눔고딕)에 없는 글자(한자 등)는 오류 |
| shape | string | no | 기본 circle |
| arc_text | string | no | 원주 상단 법인명(있으면 법인형) |
| center_text | string | no | 중심 문자. 줄바꿈은 |
| bottom_text | string | no | 원주 하단 부문자(사업자번호 등) |
| inner_ring | number | no | 이중선 두께 px |
fill_form(form_id='F_YOYANG_APPLY') 과 같다. 칸 이름: name, rrn, address, mobile, phone, accident_datetime(YYYYMMDDhhmm), hire_year/month/day, work_start, work_end, job, claim_kind_accident|disease|commute, worker_type_employee, employer_name, owner_name, workplace_phone, workplace_no(11자리),…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| values | object | yes | 칸 이름 → 값 |
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under MIT
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Workers' Compensation Application Helper (sanjae-apply) or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATrust score 99 / 100
Release 0.5.6 · scanned 4 Nov 2026
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score99
Findings0 threat · 0 capability
Capabilityminimal
Coveragesource
Verificationrepo
Surface digest1c5123dc1aca6729b319d0851709bfdc3781ff3439c50d2bae04ea26045e77ce
Score vectorthreat 100 → client 99
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | minimal | capability blast radius (minimal) — client exposure if the model is manipulated | −0 |
| verification-discount | repo | publisher verification (public source) — no provenance, but the source is public and inspectable | −1 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tool surfaceread
Implementation sourceread
Package metadataread
Live transportnot available
Tools were statically extracted from the published source (5 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. minimal is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| list_required_forms | no tags | |
| get_form_catalog | no tags | |
| fill_form | no tags | |
| make_seal | no tags | |
| fill_yoyang_apply | no tags |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
Integrityfirst-seen
Surface digest1c5123dc1aca6729
Scanned2026-11-04
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 0.5.6. Pin a release below and the command asks for exactly that one.
0.5.6
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish Workers' Compensation Application Helper (sanjae-apply) can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.