How do I find my HiBob API Token?

Log in to HiBob as an admin, go to **Settings > Integrations**, and look for the **Service Users** section. Create a new service user or select an existing one to generate and copy the API Token.

Why should I use the 'search_employees' tool?

The `search_employees` tool uses the modern HiBob Search API, which is more powerful than legacy endpoints and supports retrieving custom fields and filtering active/inactive status efficiently.

Can I check who is currently on vacation?

Yes! Use the `get_whos_out` tool by providing a date range. It will return a list of all employees currently on leave or scheduled to be out during those dates.

Is the integration secure for HR data?

Absolutely. The integration uses official HiBob Service User tokens over HTTPS. Your credentials and employee data are encrypted and stored securely within the Vinkius Cloud infrastructure.

HiBob MCP Server for Pydantic AI 11 tools — connect in under 2 minutes

Name: HiBob
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 11 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect HiBob through Vinkius and every tool is automatically validated against Pydantic schemas. catch errors at build time, not in production.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

    agent = Agent(
        model="openai:gpt-4o",
        mcp_servers=[server],
        system_prompt=(
            "You are an assistant with access to HiBob "
            "(11 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in HiBob?"
    )
    print(result.data)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About HiBob MCP Server

Connect your HiBob HR platform to any AI agent and take full control of your people management and organizational data through natural conversation.

Pydantic AI validates every HiBob tool response against typed schemas, catching data inconsistencies at build time. Connect 11 tools through Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code. full type safety, structured output guarantees, and dependency injection for testable agents.

What you can do

Employee Search — Perform advanced searches for employees, retrieve full profiles, and access custom fields.
Time Off Oversight — Monitor who is out of the office, check leave balances, and submit new time off requests.
Task Management — List all open HR tasks and mark them as completed directly from the chat interface.
Payroll & Compensation — Access historical payroll data and retrieve detailed compensation packages for employees.
Operational Efficiency — Send welcome invitations to new hires and monitor organizational lists and configurations.
Public Profiles — Quickly retrieve basic contact information for any active member of your organization.

The HiBob MCP Server exposes 11 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect HiBob to Pydantic AI via MCP

Follow these steps to integrate the HiBob MCP Server with Pydantic AI.

Install Pydantic AI

Run pip install pydantic-ai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 11 tools from HiBob with type-safe schemas

Why Use Pydantic AI with the HiBob MCP Server

Pydantic AI provides unique advantages when paired with HiBob through the Model Context Protocol.

Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application

Model-agnostic architecture. switch between OpenAI, Anthropic, or Gemini without changing your HiBob integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your HiBob connection logic from agent behavior for testable, maintainable code

HiBob + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the HiBob MCP Server delivers measurable value.

Type-safe data pipelines: query HiBob with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple HiBob tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query HiBob and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock HiBob responses and write comprehensive agent tests

HiBob MCP Tools for Pydantic AI (11)

These 11 tools become available when you connect HiBob to Pydantic AI via MCP:

complete_task

Mark a specific task as completed

get_employee_compensation

Get detailed salary and benefit information for an employee

get_leave_balance

Get the leave balance for a specific employee

get_payroll_history

Retrieve platform payroll history

get_whos_out

List employees on leave for a specific date range

invite_employee

Send a welcome invitation to a new employee

list_company_settings_lists

List custom dropdown and configuration lists used in the platform

list_open_tasks

List all pending tasks across the company

list_public_profiles

List basic contact information for all active employees

request_time_off

Pass the payload as a JSON string in "request_json" (requires policyType, startDate, endDate). Submit a new time off request for an employee

search_employees

Pass search criteria as a JSON string in "search_json". Returns active employees by default. Search for employees using filters and retrieve profiles

Example Prompts for HiBob in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with HiBob immediately.

"Search for employees in the 'Engineering' department."

"Check who is out of the office this week."

"Show my open HR tasks and complete ID 'task_992'."

Troubleshooting HiBob MCP Server with Pydantic AI

Common issues when connecting HiBob to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

HiBob + Pydantic AI FAQ

Common questions about integrating HiBob MCP Server with Pydantic AI.

How does Pydantic AI discover MCP tools?

Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.

Does Pydantic AI validate MCP tool responses?

Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.

Can I switch LLM providers without changing MCP code?

Absolutely. Pydantic AI abstracts the model layer. your HiBob MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.