# kiwiHR MCP by usefulapi (remote · kiwihr.usefulapi.io)

Read kiwiHR employees, time off, timesheets, projects; create and update employees, timesheets.

- Trust score: 62/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-25

## Components

- remote · `kiwihr.usefulapi.io`: 62/100 (this document), [markdown](https://verifymcp.io/servers/io-usefulapi-kiwihr/kiwihr.md), [page](https://verifymcp.io/servers/io-usefulapi-kiwihr/kiwihr)

## Channel facts

- Endpoint: `https://kiwihr.usefulapi.io/mcp`
- Transports: `streamable-http`
- Auth: `required`
- Version: `1.0.3`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-10-25.

- **Endpoint Security**: 78/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation is enforced on tool calls, advertised via RFC 9728 protected-resource metadata. Discovery is public, which costs nothing: no tool can be invoked without a token.
  - HTTPS enforcement could not be verified: the plaintext port redirected somewhere other than https, so enforcement is unproven.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
  - The authorisation server offers only Dynamic Client Registration (RFC 7591), which MCP 2026-07-28 deprecated in favour of Client ID Metadata Documents.
- **Transport & Reachability**: 0/100
  - Transport check failed: declared streamable-http, but the endpoint redirected instead of responding directly.
- **Schema Quality & AI Usability**: 78/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 4138 tokens (~137/item across 30 items; 30 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 3/100
  - Stability observed for 1 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 95/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 85% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - All 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.
  - An AI judge read all 31 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 60/100
  - Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28.

## Install

### How do I install the kiwiHR MCP by usefulapi server?

kiwiHR MCP by usefulapi is a hosted endpoint at https://kiwihr.usefulapi.io/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http io-usefulapi-kiwihr 'https://kiwihr.usefulapi.io/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "io-usefulapi-kiwihr": {
      "url": "https://kiwihr.usefulapi.io/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "io-usefulapi-kiwihr": {
      "type": "http",
      "url": "https://kiwihr.usefulapi.io/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.io-usefulapi-kiwihr]
url = "https://kiwihr.usefulapi.io/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "io-usefulapi-kiwihr": {
      "type": "remote",
      "url": "https://kiwihr.usefulapi.io/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add io-usefulapi-kiwihr --url 'https://kiwihr.usefulapi.io/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  io-usefulapi-kiwihr:
    url: "https://kiwihr.usefulapi.io/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "io-usefulapi-kiwihr": {
      "Transport": "http",
      "Url": "https://kiwihr.usefulapi.io/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add io-usefulapi-kiwihr -t streamable-http -u 'https://kiwihr.usefulapi.io/mcp'
```

### Other

```json
{
  "mcpServers": {
    "io-usefulapi-kiwihr": {
      "type": "http",
      "url": "https://kiwihr.usefulapi.io/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-10-25 (score 62, +1)

- [functional improvement] Stability: unverified → 0.03
- [functional] Server version: 1.0.0 → 1.0.3

### 2026-10-24 (score 61)

First indexed and scored.

## MCP tools (30)

### `kiwihr_list_users` (~287 tokens)

List employees

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.

Input parameters:

- `email` (string): Work e-mail contains this text.
- `employment_start_from` (string): Only employees who started on or after this date.
- `first_name` (string): First name contains this text.
- `is_active` (boolean): true = active employees only, false = deactivated only. Omit for both.
- `last_name` (string): Last name contains this text.
- `limit` (integer): Items per page (1-100, default 50).
- `location_id` (string): Location id (from kiwihr_list_locations).
- `offset` (integer): Items to skip (default 0). The reply's pageInfo.next says whether there is another page.
- `position_id` (string): Position id (from kiwihr_list_positions).
- `sort_by` (string): Sort field.
- `sort_direction` (string): Sort direction (default ASC).
- `team_id` (string): Team id (from kiwihr_list_teams).
- `user_ids` (array): Only these employee ids.

### `kiwihr_get_user` (~140 tokens)

Get employee

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 never returned. GraphQL query user.

Input parameters:

- `include_personal` (boolean): Also return private data (birth date, private contact data, address, emergency contact). Default false.
- `user_id` (string, required): Employee id.

### `kiwihr_list_teams` (~104 tokens)

List teams

List teams and departments (id, name, kind GROUP or DEPARTMENT). Use the ids to filter employees. GraphQL query teams.

Input parameters:

- `limit` (integer): Items per page (1-100, default 50).
- `offset` (integer): Items to skip (default 0). The reply's pageInfo.next says whether there is another page.
- `sort_by` (string)
- `sort_direction` (string): Sort direction (default ASC).

### `kiwihr_list_locations` (~96 tokens)

List locations

List office locations (id, name). Use the ids to filter employees. GraphQL query locations.

Input parameters:

- `limit` (integer): Items per page (1-100, default 50).
- `offset` (integer): Items to skip (default 0). The reply's pageInfo.next says whether there is another page.
- `sort_by` (string)
- `sort_direction` (string): Sort direction (default ASC).

### `kiwihr_list_positions` (~96 tokens)

List positions

List job positions (id, name). Use the ids to filter employees. GraphQL query positions.

Input parameters:

- `limit` (integer): Items per page (1-100, default 50).
- `offset` (integer): Items to skip (default 0). The reply's pageInfo.next says whether there is another page.
- `sort_by` (string)
- `sort_direction` (string): Sort direction (default ASC).

### `kiwihr_list_custom_fields` (~122 tokens)

List custom fields

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.

Input parameters:

- `limit` (integer): Items per page (1-100, default 50).
- `offset` (integer): Items to skip (default 0). The reply's pageInfo.next says whether there is another page.
- `sort_by` (string)
- `sort_direction` (string): Sort direction (default ASC).

### `kiwihr_list_time_off_types` (~129 tokens)

List time off types

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.

Input parameters:

- `limit` (integer): Items per page (1-100, default 50).
- `offset` (integer): Items to skip (default 0). The reply's pageInfo.next says whether there is another page.
- `sort_by` (string)
- `sort_direction` (string): Sort direction (default ASC).

### `kiwihr_list_time_off_balances` (~182 tokens)

List time off balances

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.

Input parameters:

- `is_active` (boolean): true = active balances only.
- `sort_by` (string)
- `sort_direction` (string): Sort direction (default ASC).
- `time_off_type_id` (string): Only this time off type (from kiwihr_list_time_off_types).
- `usage_period_end_to` (string): Usage period ends on or before this date.
- `usage_period_start_from` (string): Usage period starts on or after this date.

### `kiwihr_get_time_off_usage` (~234 tokens)

Get time off usage

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.

Input parameters:

- `date_from` (string, required): Range start (YYYY-MM-DD).
- `date_to` (string, required): Range end (YYYY-MM-DD).
- `is_active` (boolean): true = active employees only.
- `limit` (integer): Items per page (1-100, default 50).
- `location_id` (string): Only employees at this location.
- `offset` (integer): Items to skip (default 0). The reply's pageInfo.next says whether there is another page.
- `sort_by` (string)
- `sort_direction` (string): Sort direction (default ASC).
- `team_id` (string): Only employees of this team.
- `time_off_type_ids` (array, required): Time off type ids (from kiwihr_list_time_off_types).

### `kiwihr_list_timesheets` (~175 tokens)

List timesheets

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.

Input parameters:

- `date_from` (string, required): Range start (YYYY-MM-DD).
- `date_to` (string, required): Range end (YYYY-MM-DD).
- `limit` (integer): Days per page (1-100, default 50).
- `offset` (integer): Items to skip (default 0). The reply's pageInfo.next says whether there is another page.
- `user_id` (string): Employee id. Omit for the admin user the API key acts as.

### `kiwihr_get_timesheet` (~92 tokens)

Get timesheet

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.

Input parameters:

- `date` (string, required): Day (YYYY-MM-DD).
- `user_id` (string): Employee id. Omit for the admin user the API key acts as.

### `kiwihr_get_attendance_statement` (~96 tokens)

Get attendance statement

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.

Input parameters:

- `date_from` (string, required): Range start (YYYY-MM-DD).
- `date_to` (string, required): Range end (YYYY-MM-DD).
- `user_id` (string, required): Employee id.

### `kiwihr_list_attendance_statements` (~178 tokens)

List attendance statements

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.

Input parameters:

- `date_from` (string, required): Range start (YYYY-MM-DD).
- `date_to` (string, required): Range end (YYYY-MM-DD).
- `has_uncategorized_time` (boolean): true = only employees with tracked time not assigned to any project.
- `include_inactive_users` (boolean): Also include deactivated employees (default false).
- `project_id` (string): Only employees with tracked time in this project.
- `sort_by` (string)
- `sort_direction` (string): Sort direction (default ASC).

### `kiwihr_list_overtime_balances` (~95 tokens)

List overtime balances

Current overtime balance (seconds) per employee. GraphQL query overtimeBalanceStatements.

Input parameters:

- `limit` (integer): Items per page (1-100, default 50).
- `offset` (integer): Items to skip (default 0). The reply's pageInfo.next says whether there is another page.
- `sort_by` (string)
- `sort_direction` (string): Sort direction (default ASC).

### `kiwihr_list_projects` (~109 tokens)

List projects

List time-tracking projects (id, name, status ACTIVE or INACTIVE). GraphQL query projects.

Input parameters:

- `limit` (integer): Items per page (1-100, default 50).
- `offset` (integer): Items to skip (default 0). The reply's pageInfo.next says whether there is another page.
- `sort_by` (string)
- `sort_direction` (string): Sort direction (default ASC).
- `status` (string): Only projects with this status.

### `kiwihr_get_project` (~37 tokens)

Get project

One time-tracking project by id (name, status). GraphQL query project.

Input parameters:

- `project_id` (string, required): Project id.

### `kiwihr_list_journeys` (~170 tokens)

List journeys

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.

Input parameters:

- `assignee_ids` (array): Only journeys assigned to these employee ids.
- `journey_type_ids` (array): Only these journey types (from kiwihr_list_journey_types).
- `limit` (integer): Items per page (1-100, default 50).
- `offset` (integer): Items to skip (default 0). The reply's pageInfo.next says whether there is another page.
- `status` (string): Only journeys with this status.
- `team_ids` (array): Only journeys of employees in these teams.

### `kiwihr_get_journey` (~83 tokens)

Get journey

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.

Input parameters:

- `include_personal` (boolean): Also return the private e-mail on the journey. Default false.
- `journey_id` (string, required): Journey id.

### `kiwihr_list_journey_templates` (~101 tokens)

List journey templates

List journey templates (id, name, description, type). Use a template id with kiwihr_create_journey. GraphQL query journeyTemplates.

Input parameters:

- `journey_type_id` (string): Only templates of this journey type.
- `limit` (integer): Items per page (1-100, default 50).
- `offset` (integer): Items to skip (default 0). The reply's pageInfo.next says whether there is another page.

### `kiwihr_list_journey_types` (~86 tokens)

List journey types

List journey types such as pre-onboarding, onboarding or offboarding (id, name, key, archived date). GraphQL query journeyTypes.

Input parameters:

- `limit` (integer): Items per page (1-100, default 50).
- `offset` (integer): Items to skip (default 0). The reply's pageInfo.next says whether there is another page.

### `kiwihr_create_timesheet_entry` (~220 tokens)

Create timesheet entry

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.

Input parameters:

- `date` (string, required): Day (YYYY-MM-DD).
- `end_at` (string): End time HH:mm:ss.
- `note` (string): Note for the entry.
- `part_of_day` (string): For day-based tracking instead of start/end.
- `project_id` (string): Project id (from kiwihr_list_projects).
- `start_at` (string): Start time HH:mm:ss.
- `type` (string, required): MANUAL = worked time, BREAK = break.
- `user_id` (string): Employee id. Omit for the admin user the API key acts as.

### `kiwihr_update_timesheet_entry` (~145 tokens)

Update timesheet 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.

Input parameters:

- `end_at` (string): New end time HH:mm:ss.
- `entry_id` (string, required): Timesheet entry id.
- `note` (string): New note.
- `part_of_day` (string): New part of day.
- `project_id` (string): New project id.
- `start_at` (string): New start time HH:mm:ss.

### `kiwihr_delete_timesheet_entry` (~66 tokens)

Delete timesheet entry

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.

Input parameters:

- `entry_id` (string, required): Timesheet entry id.

### `kiwihr_create_project` (~72 tokens)

Create project

WRITE: create a time-tracking project (name, status ACTIVE or INACTIVE; default ACTIVE). Creates a new project each call (not idempotent). GraphQL mutation createProject.

Input parameters:

- `name` (string, required): Project name.
- `status` (string): ACTIVE projects can be used for time tracking.

### `kiwihr_update_project` (~77 tokens)

Update project

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.

Input parameters:

- `name` (string): New name.
- `project_id` (string, required): Project id.
- `status` (string): New status.

### `kiwihr_create_user` (~199 tokens)

Create employee

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.

Input parameters:

- `email` (string, required): Work e-mail address.
- `employment_start_date` (string): First day of employment (YYYY-MM-DD).
- `first_name` (string, required)
- `gender` (string)
- `last_name` (string, required)
- `location_id` (string): Location id (from kiwihr_list_locations).
- `manager_id` (string): Manager's employee id.
- `position_id` (string): Position id (from kiwihr_list_positions).
- `team_ids` (array): Team ids (from kiwihr_list_teams).
- `work_phones` (array)

### `kiwihr_update_user` (~171 tokens)

Update employee

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.

Input parameters:

- `about_me` (string)
- `employment_start_date` (string)
- `first_name` (string)
- `last_name` (string)
- `location_id` (string)
- `manager_id` (string)
- `position_id` (string)
- `team_ids` (array): Replaces the list of teams.
- `user_id` (string, required): Employee id.
- `work_phones` (array): Replaces the list of work phones.

### `kiwihr_deactivate_user` (~66 tokens)

Deactivate employee

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.

Input parameters:

- `user_id` (string, required): Employee id.

### `kiwihr_activate_user` (~48 tokens)

Activate employee

WRITE: re-activate a deactivated employee so they appear in active lists and can use kiwiHR again. GraphQL mutation activateUser.

Input parameters:

- `user_id` (string, required): Employee id.

### `kiwihr_create_journey` (~189 tokens)

Create journey

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.

Input parameters:

- `assignee_id` (string, required): Employee id the journey is for.
- `custom_date` (string): Custom date steps can relate to (YYYY-MM-DD).
- `custom_date_name` (string): Label of the custom date.
- `journey_template_id` (string): Journey template id.
- `journey_type_id` (string, required): Journey type id.
- `name` (string): Journey name.
- `personal_email` (string): Private e-mail (for pre-onboarding).
- `pre_onboarding_access` (boolean): Enable pre-onboarding access.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/io-usefulapi-kiwihr/kiwihr#diagnostics

## Score history

- 2026-10-25: 62
- 2026-10-24: 61

## Common questions

### What is the kiwiHR MCP by usefulapi server?

kiwiHR MCP by usefulapi is listed in the public MCP registry as io.usefulapi/kiwihr. Read kiwiHR employees, time off, timesheets, projects; create and update employees, timesheets. This page covers its hosted endpoint (https://kiwihr.usefulapi.io/mcp).

### Is the kiwiHR MCP by usefulapi server safe to use?

kiwiHR MCP by usefulapi scores 62 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the kiwiHR MCP by usefulapi server expose?

kiwiHR MCP by usefulapi exposes 30 tools: kiwihr_list_users, kiwihr_get_user, kiwihr_list_teams, kiwihr_list_locations, kiwihr_list_positions, and 25 more. Their descriptions and schemas cost roughly 3,865 tokens of context every time the server is loaded.

### Does the kiwiHR MCP by usefulapi server require authentication?

Yes. kiwiHR MCP by usefulapi asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.

### Is the kiwiHR MCP by usefulapi server still maintained?

kiwiHR MCP by usefulapi is still listed as active in the MCP registry. We last reached this channel on 25 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://kiwihr.usefulapi.io/mcp
- Repository: https://github.com/m190/usefulapi-mcp
- Website: https://usefulapi.io/kiwihr/
- Changelog RSS feed: https://verifymcp.io/servers/io-usefulapi-kiwihr/kiwihr.xml
- Changelog JSON feed: https://verifymcp.io/servers/io-usefulapi-kiwihr/kiwihr.json
- HTML version of this page: https://verifymcp.io/servers/io-usefulapi-kiwihr/kiwihr