How to Use the HiBob MCP in LlamaIndex

Q: Can I use LlamaIndex to search employees using the HiBob searchemployees tool?

Yes, you can register the searchemployees tool as a query tool spec within your LlamaIndex agent. The agent will execute the search and index the returned HiBob profiles to answer specific directory queries.

Q: How do I handle real-time updates for getwhosout in LlamaIndex?

Set up a recurring indexing task in LlamaIndex that calls getwhosout. This keeps your vector store updated with current HiBob leave data, ensuring your query engine always knows who is out of the office.

Q: Does the HiBob MCP Server support semantic search out of the box with LlamaIndex?

The server provides raw HiBob data tools like listpublicprofiles, which LlamaIndex then embeds into your vector database. This combination enables semantic search over your entire employee directory.

Index live HiBob HR data directly into your LlamaIndex vector store to ground your agent's answers in real-time facts.

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 LlamaIndex

Create your Vinkius account to connect HiBob to LlamaIndex 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 LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build a searchable HR knowledge base with LlamaIndex

Running `list_public_profiles` and `get_whos_out` lets LlamaIndex build a fully searchable, real-time HR knowledge base. This MCP Server lets you query live directories and index the fresh HiBob results directly into your vector store for instant semantic search. When employees ask who is on leave, LlamaIndex pulls the latest status to ground the response. Our integration guarantees your LlamaIndex agent provides accurate, real-time answers instead of guessing or hallucinating.

Ground RAG pipelines in actual compensation data

Retrieving `get_employee_compensation` through LlamaIndex grounds your RAG pipelines in actual, real-time salary details. Your LlamaIndex pipeline can fetch raw numbers and combine them with your internal compensation guidelines to answer complex equity questions. This integration ensures that highly sensitive HiBob financial details are retrieved only when requested by LlamaIndex. Mapping these tool outputs directly into your query engine keeps the context window clean and relevant.

Feed company configuration lists into your index

Calling `list_company_settings_lists` ensures your LlamaIndex search index stays fully aligned with your current corporate structure. By calling this tool via the MCP Server, your agent indexes the exact custom dropdown values and department names used in your HiBob portal. This prevents search errors when users look up specific team structures in LlamaIndex. LlamaIndex uses these indexed HiBob configurations to map natural language queries to the exact terms used in your database.

Setup guide

Set up HiBob MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all HiBob MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to HiBob tools.",
)
response = await agent.run("List recent HiBob data")

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 LlamaIndex

Yes, you can register the `search_employees` tool as a query tool spec within your LlamaIndex agent. The agent will execute the search and index the returned HiBob profiles to answer specific directory queries.

Set up a recurring indexing task in LlamaIndex that calls `get_whos_out`. This keeps your vector store updated with current HiBob leave data, ensuring your query engine always knows who is out of the office.

The server provides raw HiBob data tools like `list_public_profiles`, which LlamaIndex then embeds into your vector database. This combination enables semantic search over your entire employee directory.

You can filter the HiBob tools during initialization by passing an allowed list to the LlamaIndex tool spec. This lets you exclude sensitive tools if your agent only needs directory access.

All employee profile records and contact details retrieved via `list_public_profiles` are processed strictly in memory and never written to disk. Your LlamaIndex pipeline communicates with the server through a secure, single-token endpoint that you control, preventing unauthorized access to employee records.

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