Comprehensive Model Context Protocol server for managing Home Assistant through AI assistants.
kiwiHR MCP by usefulapi 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.
What it does
Read kiwiHR employees, time off, timesheets, projects; create and update employees, timesheets.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http kiwihr-mcp-by-usefulapi https://kiwihr.usefulapi.io/mcp
# 2 — ask your agent for something these tools do
# kiwihr_list_users, kiwihr_get_user, kiwihr_list_teams and 27 more
kiwiHR MCP by usefulapi costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. Nothing here runs on your machine and nothing runs on ours: this server answers at its publisher’s own address, and what you install is the connection straight to it.
This is a public server: it answers at its publisher’s own address and this marketplace is not in the path. Claude Code registers it in one command; --scope user makes it available in every project. The transport below is http, as the publisher's own manifest declares it.
claude mcp add --scope user --transport http kiwihr-mcp-by-usefulapi https://kiwihr.usefulapi.io/mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
One config entry pointing straight at the publisher’s own address — this marketplace is not in the path, and nothing from this listing executes on your machine.
30 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.
List or search employees (kiwiHR 'users') with name, work email, active flag, employee number, employment dates, position, team, location and manager. Filter by active state, team, location, position, e-mail or name. Payroll, bank, tax and insurance data are never included. GraphQL query users.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| is_active | boolean | no | true = active employees only, false = deactivated only. Omit for both. |
| team_id | string | no | Team id (from kiwihr_list_teams). |
| location_id | string | no | Location id (from kiwihr_list_locations). |
| position_id | string | no | Position id (from kiwihr_list_positions). |
| user_ids | array | no | Only these employee ids. |
| string | no | Work e-mail contains this text. | |
| first_name | string | no | First name contains this text. |
| last_name | string | no | Last name contains this text. |
| employment_start_from | string | no | Only employees who started on or after this date. |
| sort_by | string | no | Sort field. |
| sort_direction | string | no | Sort direction (default ASC). |
| offset | integer | no | Items to skip (default 0). The reply's pageInfo.next says whether there is another page. |
| limit | integer | no | Items per page (1-100, default 50). |
One employee by id: the list fields plus probation end, about-me, language, invitation status, work phones, all teams, work schedule and custom field values. With include_personal=true it also returns birth date, private e-mail and phone, nationality, gender, pronouns, home address, emergency contact and custom fields of the personal sections. Payroll, bank (IBAN/BIC), tax and insurance data are n
| Parameter | Type | Required | Notes |
|---|---|---|---|
| user_id | string | yes | Employee id. |
| include_personal | boolean | no | Also return private data (birth date, private contact data, address, emergency contact). Default false. |
List teams and departments (id, name, kind GROUP or DEPARTMENT). Use the ids to filter employees. GraphQL query teams.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| sort_by | string | no | — |
| sort_direction | string | no | Sort direction (default ASC). |
| offset | integer | no | Items to skip (default 0). The reply's pageInfo.next says whether there is another page. |
| limit | integer | no | Items per page (1-100, default 50). |
List office locations (id, name). Use the ids to filter employees. GraphQL query locations.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| sort_by | string | no | — |
| sort_direction | string | no | Sort direction (default ASC). |
| offset | integer | no | Items to skip (default 0). The reply's pageInfo.next says whether there is another page. |
| limit | integer | no | Items per page (1-100, default 50). |
List job positions (id, name). Use the ids to filter employees. GraphQL query positions.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| sort_by | string | no | — |
| sort_direction | string | no | Sort direction (default ASC). |
| offset | integer | no | Items to skip (default 0). The reply's pageInfo.next says whether there is another page. |
| limit | integer | no | Items per page (1-100, default 50). |
List the company's custom employee profile fields (id, name, section, data type, choice options). Payroll and bank sections are listed by name only; their values are never returned by any tool. GraphQL query customFields.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| sort_by | string | no | — |
| sort_direction | string | no | Sort direction (default ASC). |
| offset | integer | no | Items to skip (default 0). The reply's pageInfo.next says whether there is another page. |
| limit | integer | no | Items per page (1-100, default 50). |
List time off (absence) types such as vacation or sick leave: id, name, colour, visibility to team members. Use the ids with kiwihr_get_time_off_usage and kiwihr_list_time_off_balances. GraphQL query timeOffTypes.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| sort_by | string | no | — |
| sort_direction | string | no | Sort direction (default ASC). |
| offset | integer | no | Items to skip (default 0). The reply's pageInfo.next says whether there is another page. |
| limit | integer | no | Items per page (1-100, default 50). |
Time off balances of all employees: per employee and time off rule the allowance, accrued, used, requested, planned and available days, carry-over and the accrual/usage periods. Filter by time off type, active state and usage period. The API has no per-employee filter or paging for this query; read the result per user. GraphQL query timeOffBalances.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| time_off_type_id | string | no | Only this time off type (from kiwihr_list_time_off_types). |
| is_active | boolean | no | true = active balances only. |
| usage_period_start_from | string | no | Usage period starts on or after this date. |
| usage_period_end_to | string | no | Usage period ends on or before this date. |
| sort_by | string | no | — |
| sort_direction | string | no | Sort direction (default ASC). |
Who took (or requested) how much time off in a date range: per employee the request count and used days for each time off rule of the chosen time off types. Use it for absence reports ('who was off in March?'). Optional employee filters as in kiwihr_list_users. GraphQL query timeOffRequestUsageStatements.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| date_from | string | yes | Range start (YYYY-MM-DD). |
| date_to | string | yes | Range end (YYYY-MM-DD). |
| time_off_type_ids | array | yes | Time off type ids (from kiwihr_list_time_off_types). |
| team_id | string | no | Only employees of this team. |
| location_id | string | no | Only employees at this location. |
| is_active | boolean | no | true = active employees only. |
| sort_by | string | no | — |
| sort_direction | string | no | Sort direction (default ASC). |
| offset | integer | no | Items to skip (default 0). The reply's pageInfo.next says whether there is another page. |
| limit | integer | no | Items per page (1-100, default 50). |
Daily timesheets of one employee (or the key's admin user when user_id is omitted) in a date range: expected, tracked, time off, holiday and break time in SECONDS, approval flag, time offs, holidays, entries (start/end, type, note, project) and break-rule violations. GraphQL query timesheets.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| user_id | string | no | Employee id. Omit for the admin user the API key acts as. |
| date_from | string | yes | Range start (YYYY-MM-DD). |
| date_to | string | yes | Range end (YYYY-MM-DD). |
| offset | integer | no | Items to skip (default 0). The reply's pageInfo.next says whether there is another page. |
| limit | integer | no | Days per page (1-100, default 50). |
The timesheet of ONE employee for ONE day (user_id omitted = the admin user the key acts as), with all entries and their ids (needed to update or delete an entry). Times in seconds. GraphQL query timesheet.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| user_id | string | no | Employee id. Omit for the admin user the API key acts as. |
| date | string | yes | Day (YYYY-MM-DD). |
Attendance summary of ONE employee over a date range: expected, tracked, total, time off and holiday time (seconds) and days, balance, overtime, meal vouchers, and tracked time per project. GraphQL query attendanceStatement.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| user_id | string | yes | Employee id. |
| date_from | string | yes | Range start (YYYY-MM-DD). |
| date_to | string | yes | Range end (YYYY-MM-DD). |
Attendance summaries of ALL employees over a date range (expected vs tracked time, time off, holidays, balance, overtime, tracked time per project). Optionally only employees with time tracked on a project, or with uncategorized time; inactive employees can be included. GraphQL query attendanceStatements.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| date_from | string | yes | Range start (YYYY-MM-DD). |
| date_to | string | yes | Range end (YYYY-MM-DD). |
| project_id | string | no | Only employees with tracked time in this project. |
| has_uncategorized_time | boolean | no | true = only employees with tracked time not assigned to any project. |
| include_inactive_users | boolean | no | Also include deactivated employees (default false). |
| sort_by | string | no | — |
| sort_direction | string | no | Sort direction (default ASC). |
Current overtime balance (seconds) per employee. GraphQL query overtimeBalanceStatements.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| sort_by | string | no | — |
| sort_direction | string | no | Sort direction (default ASC). |
| offset | integer | no | Items to skip (default 0). The reply's pageInfo.next says whether there is another page. |
| limit | integer | no | Items per page (1-100, default 50). |
List time-tracking projects (id, name, status ACTIVE or INACTIVE). GraphQL query projects.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| status | string | no | Only projects with this status. |
| sort_by | string | no | — |
| sort_direction | string | no | Sort direction (default ASC). |
| offset | integer | no | Items to skip (default 0). The reply's pageInfo.next says whether there is another page. |
| limit | integer | no | Items per page (1-100, default 50). |
One time-tracking project by id (name, status). GraphQL query project.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project_id | string | yes | Project id. |
List onboarding/offboarding journeys (id, name, status DRAFT/ONGOING/COMPLETED/CANCELLED, assignee, journey type, custom date). Filter by status, assignee, type or team. GraphQL query journeys.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| status | string | no | Only journeys with this status. |
| assignee_ids | array | no | Only journeys assigned to these employee ids. |
| journey_type_ids | array | no | Only these journey types (from kiwihr_list_journey_types). |
| team_ids | array | no | Only journeys of employees in these teams. |
| offset | integer | no | Items to skip (default 0). The reply's pageInfo.next says whether there is another page. |
| limit | integer | no | Items per page (1-100, default 50). |
One journey by id with its steps (name, description, fixed start and due dates). With include_personal=true it also returns the private e-mail address stored on the journey. GraphQL query journey.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| journey_id | string | yes | Journey id. |
| include_personal | boolean | no | Also return the private e-mail on the journey. Default false. |
List journey templates (id, name, description, type). Use a template id with kiwihr_create_journey. GraphQL query journeyTemplates.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| journey_type_id | string | no | Only templates of this journey type. |
| offset | integer | no | Items to skip (default 0). The reply's pageInfo.next says whether there is another page. |
| limit | integer | no | Items per page (1-100, default 50). |
List journey types such as pre-onboarding, onboarding or offboarding (id, name, key, archived date). GraphQL query journeyTypes.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| offset | integer | no | Items to skip (default 0). The reply's pageInfo.next says whether there is another page. |
| limit | integer | no | Items per page (1-100, default 50). |
WRITE: add a time entry to the timesheet of one employee on one day (user_id omitted = the admin user the key acts as). type MANUAL = worked time (give start_at and end_at as HH:mm:ss, or a part_of_day), BREAK = a break. Optional project and note. Creates a new entry each call (not idempotent). Returns the updated day. GraphQL mutation createTimesheetEntry.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| user_id | string | no | Employee id. Omit for the admin user the API key acts as. |
| date | string | yes | Day (YYYY-MM-DD). |
| type | string | yes | MANUAL = worked time, BREAK = break. |
| start_at | string | no | Start time HH:mm:ss. |
| end_at | string | no | End time HH:mm:ss. |
| part_of_day | string | no | For day-based tracking instead of start/end. |
| project_id | string | no | Project id (from kiwihr_list_projects). |
| note | string | no | Note for the entry. |
WRITE: change an existing timesheet entry (get its id from kiwihr_get_timesheet): times, part of day, project or note. Only the fields you pass are changed. Setting the same values again gives the same result. Returns the updated day. GraphQL mutation updateTimesheetEntry.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| entry_id | string | yes | Timesheet entry id. |
| start_at | string | no | New start time HH:mm:ss. |
| end_at | string | no | New end time HH:mm:ss. |
| part_of_day | string | no | New part of day. |
| project_id | string | no | New project id. |
| note | string | no | New note. |
WRITE, DESTRUCTIVE: permanently delete one timesheet entry by id (get it from kiwihr_get_timesheet). This cannot be undone. Returns true when deleted. GraphQL mutation deleteTimesheetEntry.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| entry_id | string | yes | Timesheet entry id. |
WRITE: create a time-tracking project (name, status ACTIVE or INACTIVE; default ACTIVE). Creates a new project each call (not idempotent). GraphQL mutation createProject.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| name | string | yes | Project name. |
| status | string | no | ACTIVE projects can be used for time tracking. |
WRITE: rename a project or switch it ACTIVE/INACTIVE (INACTIVE projects can no longer be used for time tracking). Only the fields you pass are changed. GraphQL mutation updateProject.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project_id | string | yes | Project id. |
| name | string | no | New name. |
| status | string | no | New status. |
WRITE: add a new employee record (first name, last name and work e-mail are required; optional start date, manager, teams, position, location and phones). Creates a new employee each call (not idempotent). No invitation is sent by this tool. Payroll and bank data cannot be set. GraphQL mutation createUser.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| first_name | string | yes | — |
| last_name | string | yes | — |
| string | yes | Work e-mail address. | |
| employment_start_date | string | no | First day of employment (YYYY-MM-DD). |
| manager_id | string | no | Manager's employee id. |
| team_ids | array | no | Team ids (from kiwihr_list_teams). |
| position_id | string | no | Position id (from kiwihr_list_positions). |
| location_id | string | no | Location id (from kiwihr_list_locations). |
| work_phones | array | no | — |
| gender | string | no | — |
WRITE: change an employee's work profile: name, start date, about-me, work phones, position, team(s), location, manager. Only the fields you pass are changed (team_ids replaces the whole team list). Private, payroll and bank data cannot be changed with this tool. GraphQL mutation updateUser.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| user_id | string | yes | Employee id. |
| first_name | string | no | — |
| last_name | string | no | — |
| employment_start_date | string | no | — |
| about_me | string | no | — |
| work_phones | array | no | Replaces the list of work phones. |
| position_id | string | no | — |
| team_ids | array | no | Replaces the list of teams. |
| location_id | string | no | — |
| manager_id | string | no | — |
WRITE, ACCESS-CHANGING: deactivate an active employee (typically after they leave): they lose access to kiwiHR and drop out of active lists. Reversible with kiwihr_activate_user. GraphQL mutation deactivateUser.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| user_id | string | yes | Employee id. |
WRITE: re-activate a deactivated employee so they appear in active lists and can use kiwiHR again. GraphQL mutation activateUser.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| user_id | string | yes | Employee id. |
WRITE: create an onboarding/offboarding journey for an employee from a journey type and optionally a template (ids from kiwihr_list_journey_types / kiwihr_list_journey_templates). Creates a new journey each call (not idempotent). It does not publish it; check the status in the reply. GraphQL mutation createJourney.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| journey_type_id | string | yes | Journey type id. |
| assignee_id | string | yes | Employee id the journey is for. |
| journey_template_id | string | no | Journey template id. |
| name | string | no | Journey name. |
| personal_email | string | no | Private e-mail (for pre-onboarding). |
| custom_date | string | no | Custom date steps can relate to (YYYY-MM-DD). |
| custom_date_name | string | no | Label of the custom date. |
| pre_onboarding_access | boolean | no | Enable pre-onboarding access. |
- Every tool — any call limit is its publisher’s, not ours
- No card, and mcprush charges nothing for it
- Runs at its publisher’s own address — this marketplace is not in the path
- 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 kiwiHR MCP by usefulapi or to call it, at any volume.
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.
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| coverage-honesty | manifest | inspection depth (manifest) — how much of the target the scan could see | −4 |
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.
The scan read each tool’s name, description, input schema and annotations exactly as the server listed them the last time it answered us; no code was reviewed. We ask the server again about once a month, and a list that changed is graded again.
The implementation source was not read — this reflects the declared tool metadata only.
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. moderate is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| kiwihr_list_users | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| kiwihr_get_user | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| kiwihr_list_teams | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| kiwihr_list_locations | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| kiwihr_list_positions | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| kiwihr_list_custom_fields | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| kiwihr_list_time_off_types | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| kiwihr_list_time_off_balances | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| kiwihr_get_time_off_usage | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| kiwihr_list_timesheets | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| kiwihr_get_timesheet | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| kiwihr_get_attendance_statement | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| kiwihr_list_attendance_statements | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| kiwihr_list_overtime_balances | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| kiwihr_list_projects | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| kiwihr_get_project | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| kiwihr_list_journeys | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| kiwihr_get_journey | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| kiwihr_list_journey_templates | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| kiwihr_list_journey_types | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| kiwihr_create_timesheet_entry | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| kiwihr_update_timesheet_entry | external-sink | external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true |
| kiwihr_delete_timesheet_entry | external-sink | external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true |
| kiwihr_create_project | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| kiwihr_update_project | external-sink | external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true |
| kiwihr_create_user | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| kiwihr_update_user | external-sink | external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true |
| kiwihr_deactivate_user | external-sink | external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true |
| kiwihr_activate_user | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| kiwihr_create_journey | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
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.
Supply chain and provenance
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
This is an address its publisher runs: which release it serves is theirs to choose, so there is nothing here to pin. The history below is for reading; the current release on file is 1.14.3.
No release note was published with this version.
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.
Any signed-in account that does not publish kiwiHR MCP by usefulapi can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
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.