Connect
Optimize
Secure
Live 44 Actions
KiwiHR MCP Server
for AI Agents
Connect your AI agent to StackOne's KiwiHR MCP server and give it 44 MCP tools out of the box. Auth, tool execution, and security all managed.
KiwiHR MCP Server
Built by 
StackOne
StackOne 
Coverage
44 Agent Actions
Create, read, update, and delete across KiwiHR — and extend your agent's capabilities with custom actions.
Authentication
Agent Tool Authentication
Per-user OAuth in one call. Your KiwiHR MCP server gets session-scoped tokens with zero credentials stored on your infra.
Agent Auth →
Security
Agent Protection
Every KiwiHR tool response scanned for prompt injection in milliseconds — 88.7% accuracy, all running on CPU.
Prompt Injection Defense →
Performance
Max Agent Context. Min Cost.
Free up to 96% of your agent's context window to enhance reasoning and reduce cost, on every KiwiHR call.
Tools Discovery →What is the KiwiHR MCP Server?
A KiwiHR MCP server lets AI agents read and write KiwiHR data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's KiwiHR MCP server ships with 44 pre-built actions, fully extensible via the Connector Builder — plus managed authentication, prompt injection defense, observability, and agent execution runtime. Connect it from MCP clients like Claude Desktop, Claude Code, Cursor, Goose, and VS Code, or from agent frameworks like OpenAI Agents SDK, LangChain, and Vercel AI SDK.
All KiwiHR MCP Tools
Every action from KiwiHR's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.
Users
- Create User
Create a new user in the company.
- List Users
Retrieve a paginated list of users in the company.
- Get User
Retrieve a single user by ID.
- Update User
Update an existing user's profile.
- Delete User
Permanently delete a user by ID.
Timesheets
- List Timesheets
Retrieve a paginated list of timesheets for a date range.
- Get Timesheet
Retrieve a single timesheet for a specific date.
Timesheet Entrys
- Create Timesheet Entry
Create a new timesheet entry (type MANUAL, BREAK, or TRACKER) for a specific date.
- Update Timesheet Entry
Update an existing timesheet entry.
- Delete Timesheet Entry
Delete a timesheet entry by ID.
Attendance Statements
- Get Attendance Statement
Retrieve the attendance statement for a specific user and date range.
- List Attendance Statements
Retrieve a paginated list of attendance statements filtered by date range.
Journeys
- Create Journey
Create a new journey and assign it to an employee.
- List Journeys
Retrieve a paginated list of journeys assigned to employees.
- Get Journey
Retrieve a single journey by ID.
- Update Journey
Update an existing journey by ID.
- Delete Journey
Delete a journey by ID.
Journey Templates
- List Journey Templates
Retrieve a paginated list of journey templates available in the company.
- Get Journey Template
Retrieve a single journey template by ID.
Projects
- Create Project
Create a new project in the company.
- List Projects
Retrieve a paginated list of projects in the company.
- Get Project
Retrieve a single project by ID.
- Update Project
Update an existing project by ID.
- Delete Project
Delete a project by ID.
Collections
- List Collections
Retrieve a paginated list of all collections in the company.
- Get Collection
Retrieve a single collection by ID.
Custom Fields
- List Custom Fields
Retrieve a paginated list of custom field definitions for the company.
- Get Custom Field
Retrieve a single custom field definition by ID.
Other (16)
- List Available Managers
Retrieve a paginated list of users available to be assigned as managers.
- List Time Off Balances
Retrieve a paginated list of time off balances for all users.
- List Time Off Types
Retrieve a paginated list of time off types configured in the company.
- List Time Off Request Usage Statements
Retrieve time off request usage statements for a date range and time off type IDs.
- List Journey Types
Retrieve a paginated list of journey types (e.g. onboarding, offboarding).
- Get Collection Item
Retrieve a single collection item record by ID.
- List User Collections
Retrieve a paginated list of collections populated with a specific user's data.
- List User Scope Collection Items
Retrieve all collection items for a specific collection, optionally filtered by user.
- List Overtime Balance Statements
Retrieve a paginated list of overtime balance statements for all employees.
- List Overtime Balance Transactions
Retrieve a paginated list of overtime balance transactions for a specific user.
- List Locations
Retrieve a paginated list of work locations in the company.
- List Teams
Retrieve a paginated list of teams (departments) in the company.
- List Positions
Retrieve a paginated list of job positions in the company.
- Test Connection
Verifies the API key is valid by fetching a minimal user list.
- Activate User
Activate a deactivated user by ID.
- Deactivate User
Deactivate an active user by ID.
KiwiHR AI Agent Use Cases
Connect your AI agent to KiwiHR and help your team scale the HR operations they run by hand today.
Employee Onboarding
Use StackOne to connect your AI agent to your HRIS, identity management, and LMS to automate employee onboarding.
View HR Policy Q&A Chatbot
Use StackOne to connect your AI agent to your HRIS, knowledge base, and messaging tools to automate HR policy Q&A.
View Employee Offboarding
Use StackOne to connect your AI agent to your HRIS, identity management, and ITSM to automate employee offboarding and deprovisioning.
ViewSet Up Your KiwiHR MCP Server in Minutes
One endpoint. Any framework. Your agent is talking to KiwiHR in under 10 lines of code.
Agent Frameworks
JSON{
"mcpServers": {
"stackone": {
"command": "npx",
"args": [
"-y",
"mcp-remote@latest",
"https://api.stackone.com/mcp?x-account-id=<account_id>",
"--header",
"Authorization: Basic <YOUR_BASE64_TOKEN>"
]
}
}
}Check More hr-workforce MCP Servers
Phenom
87+ actions
Loket
61+ actions
Employment Hero
51+ actions
ADP Workforce Now
50+ actions
ClayHR
50+ actions
CatalystOne
36+ actions
PrismHR
30+ actions
Platform Resources
MCP Code Mode: Keeping Tool Responses Out of Agent Context
Anthropic's code_execution processes data already in context. Custom MCP code mode keeps raw tool responses in a sandbox. 14K tokens vs 500.
11 min
Comparing BM25, TF-IDF, and Hybrid Search for MCP Tool Discovery
Benchmarking BM25, TF-IDF, and hybrid search for MCP tool discovery across 916 tools. The 80/20 TF-IDF/BM25 hybrid hits 21% Top-1 accuracy in under 1ms.
10 min
Indirect Prompt Injection Defense for MCP Tools: A Technical Guide
MCP tools that read emails, CRM records, and tickets are indirect prompt injection vectors. Here's how we built a two-tier defense that scans tool results in ~11ms.
12 min
MCP vs A2A: Architecture, Security, and When to Use Each
MCP vs A2A: what each protocol standardizes, how they differ, their shared security risks including indirect prompt injection, and when to use one, both, or a hybrid architecture.
12 min
MCP vs API: What 200+ Connector Builds Taught Us
MCP wraps APIs, it doesn't replace them. After building 200+ connectors that serve both, here's when each approach wins.
14 min read
KiwiHR MCP Server FAQ
Does StackOne have a KiwiHR MCP server?
Yes. StackOne offers a hosted KiwiHR MCP server with 44 pre-built actions, and every action is tested and QA'd by StackOne. Connect it to Claude, Cursor, and any other MCP client, or to any agent framework through the AI Action SDK. It ships with managed agent authentication, prompt injection defense, and tool discovery with server-side execution that preserve your agent's context window and keep reasoning performance.
KiwiHR MCP server vs direct API integration — what's the difference?
A KiwiHR MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software — backend code calling KiwiHR. A KiwiHR MCP server is for AI agents — MCP clients like Claude and Cursor, plus framework agents built with OpenAI, LangChain, or Vercel AI — discovering and calling KiwiHR at runtime. StackOne provides both.
How does KiwiHR authentication work for AI agents?
KiwiHR authentication for AI agents works through a StackOne Connect Session. Create one via the dashboard or the SDK — you get an auth link and ready-to-paste config for Claude Desktop, Cursor, and other MCP clients. Your user authenticates their own KiwiHR account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via
origin_owner_id.Are KiwiHR MCP tools vulnerable to prompt injection?
Yes — KiwiHR MCP tools can be vulnerable to indirect prompt injection. Any tool that reads user-written content — documents, messages, tickets, records, or free-text fields — is a potential vector. StackOne Defender scans every tool response before it enters the agent's context — regex patterns in ~1ms, then a MiniLM classifier in ~4ms. 88.7% accuracy, CPU-only.
What is the context bloat of a KiwiHR agent and how do I avoid it?
Context bloat happens when KiwiHR tool schemas and API responses eat your KiwiHR agent's memory, preventing it from reasoning effectively. A single KiwiHR query can return a massive JSON response, and connecting multiple tools compounds the problem. Tools Discovery and Code Mode reduce context bloat — loading only relevant tools per query and keeping raw responses out of the agent's context.
Can I limit which actions my KiwiHR agent can access?
Yes — you can limit which actions your KiwiHR agent can access directly from the StackOne dashboard. Toggle actions on or off, or restrict them to specific accounts, with no code changes to your agent. Session tokens can be scoped to exact actions so if one leaks, exposure stays contained.
Can I create custom agent actions for my KiwiHR MCP server?
Yes — you can create custom agent actions for your KiwiHR MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research KiwiHR's API, generate production-ready connector YAML, test against the live API, and validate before you ship.
When should I NOT use a KiwiHR MCP server?
Skip a KiwiHR MCP server if your integration is purely software-to-software — direct KiwiHR API integration is simpler when no AI agent is involved. For deterministic, compliance-critical operations (financial transactions, regulatory reporting), direct API gives you predictable behavior without agent-driven decision-making. MCP shines when AI agents need to dynamically discover and call KiwiHR actions at runtime.
What AI frameworks and AI clients does the StackOne KiwiHR MCP server support?
The StackOne KiwiHR MCP server supports both. MCP clients (paste-and-go apps): Claude Desktop, Claude Code, Cursor, VS Code, Goose. Agent frameworks (code SDKs you build with): OpenAI Agents SDK, Anthropic, Vercel AI, Google ADK, CrewAI, Pydantic AI, LangChain, LangGraph, Azure AI Foundry.
Put your AI agents to work
All the tools you need to build and scale AI agent integrations, with best-in-class connectivity, execution, and security.