A Model Context Protocol (MCP) server for interacting with Microsoft 365 and Office services through the Graph API
Nothing to run from here
Kintai Plus (unofficial) 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.
100/100
trust score
23
tools declared
local
runs on your machine
—
downloads a day
What it does
Unofficial MCP server for Money Forward Cloud Kintai Plus (AKASHI): punches, records, man-hours
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user kintai-plus-unofficial-mcp '--' npx -y kintai-plus-mcp
# 2 — ask your agent for something these tools do
# end_of_day, log_manhours, monthly_review and 20 more
Kintai Plus (unofficial) costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
ATAll 1 server
atzzCokeK1 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 runs on your machine: your client starts Kintai Plus (unofficial) as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
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 kintai-plus-unofficial-mcp '--' npx -y kintai-plus-mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free 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 asks of you
Nothing is required, but it can take KINTAI_PLUS_TOKEN (API token used only in this process. Not stored or reissued unless KINTAI_PLUS_PERSIST_ENV_TOKEN=true. Prefer `npx kintai-plus-mcp login`.), KINTAI_PLUS_PERSIST_ENV_TOKEN (When true, store KINTAI_PLUS_TOKEN and reissue it if the expiry is unknown. Reissue invalidates the token in the environment.), KINTAI_PLUS_COMPANY_ID (Login company ID (ログイン企業ID), used with KINTAI_PLUS_TOKEN), KINTAI_PLUS_HOST (API host (the domain of the URL after you sign in)), KINTAI_PLUS_READ_ONLY (Expose read-only tools only), KINTAI_PLUS_CONFIRM_WRITES (Ask for confirmation (elicitation) before punches and man-hour changes) if you want to set them.
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
23 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.
今日の勤務と工数を確認し、工数の入力漏れがあれば入力してから退勤を打刻する
No parameter schema on file.
指定した日（既定は今日）の工数を、話した内容から入力する
| Parameter | Type | Required | Notes |
|---|---|---|---|
| date | string | no | 工数を入力する日（YYYY-MM-DD、既定は今日） |
| description | string | no | その日にやったこと（例: 設計 2 時間、定例 1 時間） |
指定した月（既定は今月）の勤務時間・残業の目安・打刻漏れをまとめる
| Parameter | Type | Required | Notes |
|---|---|---|---|
| month | string | no | 月（YYYY-MM、既定は今月） |
管理者向け: 管理下の従業員の今日の出勤状況と、残業が多くなりそうな人をまとめる
No parameter schema on file.
Admin only. List the staff (従業員) you manage, with staff ID, name, staff number (社員番号), and organization (所属). Paging is handled automatically. Optionally filter by text. Email and other personal details are not returned.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | no | Case-insensitive text to match in name, staff number, or organization. |
Admin only. Get the punches (打刻) of staff you manage for one day, with each person's status (not_started 未出勤 / working 勤務中 / on_break 休憩中 / finished 退勤済み) and time worked. Defaults to today and all staff you manage. Requests are split into groups of 50 automatically. Location and IP are omitted.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| date | no | Date (YYYY-MM-DD). Defaults to today. | |
| staffIds | array | no | Staff IDs (from list_staff). Defaults to all staff you manage. |
| includeStamps | boolean | no | Include each punch. Default false (status only). |
Admin only. Get working statuses (勤務処理) such as absence (欠勤) or business trip (出張) — labels are configured per company — for staff you manage over a period (max … days). Defaults to today and all staff you manage. Only days that have a status are returned.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| from | no | Start date (YYYY-MM-DD). Defaults to today. | |
| to | no | End date, inclusive (YYYY-MM-DD). Defaults to from. | |
| staffIds | array | no | Staff IDs (from list_staff). Defaults to all staff you manage. |
Admin only. List the members (プロジェクト従業員) and owners of a project, with names where available.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| projectId | integer | yes | — |
Get your own attendance alerts (アラート) from Kintai Plus, such as missing punches (打刻忘れ), suspected absence (欠勤疑い), late arrival (遅刻), early leave (早退), overtime threshold (残業時間閾値超え), 36 agreement (36協定), and missing man-hours (工数未入力). Optionally filter by month.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| month | no | Only alerts for this month (YYYY-MM). |
Check your own punches and working records for issues (打刻漏れチェック): missing clock out/in (退勤・出勤の打刻忘れ), break not ended (休憩戻なし), no punches on a workday, days over 12 hours, rest interval under 11 hours (勤務間インターバル), and holiday work. A missing punch is not reported when the working record already has…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| from | no | Start date (YYYY-MM-DD). | |
| to | no | End date, inclusive (YYYY-MM-DD). Defaults to yesterday. |
Create or update your own man-hours (工数) for one day: minutes per project task. Only the listed tasks are overwritten; other tasks on that day are kept. To remove an entry, use delete_manhours. Use list_projects / get_my_projects and list_tasks to find IDs. Days that are closed (締め) or fixed (確定)…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| date | yes | Date (YYYY-MM-DD). | |
| entries | array | yes | — |
Delete your own man-hours (工数) for one day and project. If taskId is omitted, ALL tasks of that project on that day are deleted. Days that are closed (締め) or fixed (確定) cannot be changed.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| date | yes | Date (YYYY-MM-DD). | |
| projectId | integer | yes | — |
| taskId | integer | no | Task to delete. Omit to delete all tasks of the project. |
Admin only. For staff you manage, estimate statutory overtime (法定時間外の目安) so far this month and project it to the month end (月末の着地予測), then list who is over or likely to exceed the threshold (default 45 hours, the standard monthly limit under a 36 agreement). Levels: over (already exceeded), likely…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| month | no | Month (YYYY-MM). Defaults to the current month. | |
| staffIds | array | no | Defaults to all staff you manage. |
| thresholdHours | integer | no | Monthly overtime threshold in hours. Default 45. |
| includeAll | boolean | no | Include staff with no risk (level ok). Default false. |
Get the signed-in employee's own profile (従業員情報): staff ID, name, organization (所属), and permission role (company_admin 企業管理者 / admin 一般管理者 / employee 従業員). Also returns today's date in Japan time.
No parameter schema on file.
List the company's projects (プロジェクト) used for man-hour tracking (工数). Optionally filter by name/code and by the date the project is active on. Use the projectId with list_tasks and save_manhours.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | no | Case-insensitive text to match in name, short name, or code. |
| activeOn | no | Only projects whose period includes this date (YYYY-MM-DD). |
List the tasks (タスク) of a project for man-hour tracking. Finished tasks (終了) are excluded unless includeFinished is true. Estimated time (見積もり) is in minutes.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| projectId | integer | yes | Project ID from list_projects or get_my_projects. |
| includeFinished | boolean | no | Include finished tasks. Default false. |
List the projects you are a member of (参加プロジェクト), with names. Use these projectIds for man-hours.
No parameter schema on file.
Get your own man-hour records (工数) per day, project, and task, in minutes, with project/task names. Defaults to this month. closed (締め) / fixed (確定) days cannot be changed. Max … days.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| from | no | Start date (YYYY-MM-DD). Defaults to the 1st of this month. | |
| to | no | End date, inclusive (YYYY-MM-DD). Defaults to the end of the month of from. |
Record a punch (打刻) now: clock_in (出勤), clock_out (退勤), direct_in (直行), direct_out (直帰), break_start (休憩入), break_end (休憩戻). The type is required. The punch is recorded at the time Kintai Plus receives it and CANNOT be edited or deleted via the API (corrections need a request in the web UI), so…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| type | string | yes | Punch type. |
| telework | boolean | no | Mark as telework (テレワーク). Only valid with clock_in. |
| force | boolean | no | — |
Get your own punch history (打刻履歴) for a period: clock in (出勤), clock out (退勤), direct in/out (直行/直帰), break start/end (休憩入/休憩戻). Defaults to today. Long periods are fetched in chunks automatically (max … days). Location and IP address are omitted by default.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| from | no | Start date (YYYY-MM-DD, Japan time). Defaults to today. | |
| to | no | End date, inclusive (YYYY-MM-DD). Defaults to from. |
Get today's work status (今日の勤務状況) in Japan time: not_started (未出勤), working (勤務中), on_break (休憩中), or finished (退勤済み), with time worked so far (excluding breaks), break time, and today's punches. Use this before punching.
No parameter schema on file.
Summarize your own working hours (勤務時間の集計) over a period: total actual working time (実働合計), work days (出勤日数), holiday work days (休日出勤日数), and an ESTIMATE of statutory overtime (法定時間外の目安), with a per-month breakdown. Defaults to the 1st of this month through today (max … days). Always tell the user…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| from | no | Start date (YYYY-MM-DD). Defaults to the 1st of this month. | |
| to | no | End date, inclusive (YYYY-MM-DD). Defaults to today. |
Get your own daily working records (勤務実績): day category (労働日 / 所定休日 / 法定休日), start/end time, and punch times. The API does not return actual working minutes or breaks, so actual minutes are the elapsed time from start to end (breaks included) and break time is unknown. Defaults to the 1st of this…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| from | no | Start date (YYYY-MM-DD). Defaults to the 1st of this month. | |
| to | no | End date, inclusive (YYYY-MM-DD). Defaults to today. |
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 Kintai Plus (unofficial) 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 100 / 100
Release 0.1.2 · scanned 31 Oct 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 score100
Findings0 threat · 0 capability
Capabilityminimal
Coveragesource
Verificationsource
Surface digest7ce11d2744e1740e704254d7594757682f144c9d92862d28e91d4c9c32b0ad04
Score vectorthreat 100 → client 100
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | minimal | capability blast radius (minimal) — client exposure if the model is manipulated | −0 |
| verification-discount | source | publisher verification (provenance) — cryptographic build provenance ties the artifact to its source | −0 |
| 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 surfacenot available
Implementation sourceread
Package metadataread
Live transportnot available
No tools were enumerated, so prompt-injection, capability and toxic-flow analysis had no tool surface to inspect. To grade a package’s real runtime tools, 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 |
|---|---|---|
| No per-tool rows for this release — see the note below. | ||
No tool surface was enumerated, so there is nothing to attribute a capability to.
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 digest7ce11d2744e1740e
Scanned2026-10-31
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 0.1.2. Pin a release below and the command asks for exactly that one.
0.1.2
31 Oct 2026
latestNo release note was published with this version.
0.1.0
undated
- The version this listing was on when mcprush began following its releases. The registry was not asked when it shipped, so this row carries no date.
—
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 Kintai Plus (unofficial) 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.