How to Use the HiBob MCP in LangChain

Connect your LangChain agents to HiBob to run multi-step HR workflows and track every tool call in LangSmith.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect HiBob MCP to LangChain

Create your Vinkius account to connect HiBob to LangChain and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup HiBob with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build multi-step HR chains in LangChain

Chaining `search_employees` and `get_leave_balance` in LangChain lets you build automated, multi-step HR workflows. Your agent can search for a user, extract their manager's ID, and then feed that exact ID into the leave tool to verify time-off requests without hardcoding variables. This MCP Server connects directly to your LangChain runnables to expose your HiBob directory. It lets you pass outputs from one tool call straight into the next step of your chain, turning manual employee lookups into automated, multi-stage logic.

Trace every HR tool execution with LangSmith

Tracking `invite_employee` and `get_payroll_history` calls via LangSmith makes debugging your onboarding pipelines incredibly simple. Every time your agent triggers an invite or checks history, LangSmith records the exact payload, latency, and token cost of the execution. Debugging complex LangChain chains becomes simple when you see the raw inputs and outputs from the HiBob API. You can pinpoint exactly where a payload mismatch occurred in your `request_time_off` JSON string before it hits your production HR database.

Manage tasks dynamically across your team

Querying `list_open_tasks` and executing `complete_task` allows your LangChain agents to manage team tasks dynamically. The agent queries outstanding actions, evaluates who is responsible, and then updates the system once the work is done. Manual follow-ups become a thing of the past in your LangChain workflows. By combining these MCP actions with LangChain memory, your runnables maintain context across multiple interactions to ensure no HiBob task falls through the cracks.

Setup guide

Set up HiBob MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes HiBob tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "hibob-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent HiBob transactions"
    })
    print(result["messages"][-1].content)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by HiBob. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect HiBob now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about HiBob MCP in LangChain

Use a structured LangChain LLM call to format the JSON payload before passing it to the HiBob tool. LangChain parses the arguments to match the schema required for the `request_time_off` tool automatically.

Yes, you can load this HiBob MCP Server alongside your database tools using the LangChain multi-server client. This lets your agent pull employee records from HiBob and write them to your local database in a single run.

You should configure your LangChain runnables with exponential backoff wrappers when calling HiBob. If the `get_payroll_history` tool hits an API limit, the LangChain chain pauses and retries the call based on your retry configuration.

Install the adapter package and use the MultiServerMCPClient to point to your Vinkius HiBob endpoint. From there, call the tool retrieval method and pass the resulting list directly into your LangChain agent's initialization step.

Yes, your sensitive employee payroll and salary records remain fully protected. Vinkius runs the MCP Server in an isolated sandbox, meaning your raw compensation and payroll data never persists on our servers. Your LangChain agent receives the data directly through an encrypted connection, keeping employee salary details private.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript