How to Use the Hurma MCP in LlamaIndex

Q: Can I use Hurma with LlamaIndex to answer questions about vacation policies?

Yes, you can combine Hurma tools like getvacationbalance with your policy documents in a unified query engine. The system will retrieve the exact balance for the employee and cross-reference it with your HR guidelines.

Q: Does LlamaIndex support real-time updates for Hurma candidate pipelines?

Yes, you can run scheduled indexing tasks that call listvacancystages and listcandidates to keep your vector store synchronized. This ensures your search results always reflect the current state of your recruitment pipeline.

Q: Is my Hurma employee and candidate data safe when indexed by LlamaIndex?

Yes, all employee details and candidate data extracted via getemployeedetails are stored within your own designated vector databases. Vinkius manages the connection securely, ensuring that no sensitive HR records are exposed to external third-party servers.

Index live Hurma HR data directly into LlamaIndex to build searchable knowledge bases for employee records and candidate pools.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Hurma MCP to LlamaIndex

Create your Vinkius account to connect Hurma 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 Hurma with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Semantic search over candidate pools with this MCP Server

The `list_candidates` tool feeds raw applicant profiles directly into your LlamaIndex vector store for indexing. Instead of clicking through profiles one by one, you can query your LlamaIndex to find Hurma candidates with specific skill sets. Your LlamaIndex agent calls `get_candidate_details` to enrich the index with deep-dive history. This creates a searchable Hurma candidate pool where natural language queries surface the best resumes in seconds.

Live RAG for employee directories and departments

Your AI system queries `list_employees` using this MCP tool to build a live LlamaIndex vector index of your current workforce. This allows team members to ask LlamaIndex natural language questions about who works in which department or who is currently active. By combining this with `list_departments`, your LlamaIndex query engine accurately routes internal questions to the correct Hurma teams. You get real-time answers grounded in actual Hurma records rather than static, outdated spreadsheets inside your LlamaIndex context.

Indexing out-of-office schedules for team queries

The `list_out_of_office` tool provides a real-time feed of employee absences that you can index for instant LlamaIndex retrieval. When someone asks if a colleague is available, the LlamaIndex engine checks the indexed Hurma records to provide an immediate status update. Coupling this with `get_vacation_balance` allows HR managers to query overall team availability trends inside LlamaIndex. This turns raw Hurma attendance data into a searchable LlamaIndex knowledge base for planning project timelines.

Setup guide

Set up Hurma 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 Hurma 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 Hurma tools.",
)
response = await agent.run("List recent Hurma 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 Hurma. 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 Hurma 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 Hurma MCP in LlamaIndex

You initialize the LlamaIndex MCP tool spec with your Vinkius endpoint to fetch tools like `list_employees`. From there, load the tool outputs into documents and index them using a standard vector store index.

Yes, you can combine Hurma tools like `get_vacation_balance` with your policy documents in a unified query engine. The system will retrieve the exact balance for the employee and cross-reference it with your HR guidelines.

Yes, you can run scheduled indexing tasks that call `list_vacancy_stages` and `list_candidates` to keep your vector store synchronized. This ensures your search results always reflect the current state of your recruitment pipeline.

You can use the allowed tools filter during the client setup to restrict access to sensitive tools. For instance, you can expose only `list_departments` while blocking tools that modify data.

Yes, all employee details and candidate data extracted via `get_employee_details` are stored within your own designated vector databases. Vinkius manages the connection securely, ensuring that no sensitive HR records are exposed to external third-party servers.

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