How to Use the Hurma MCP in LangChain

Q: Can I combine Hurma tools with other APIs in a single chain?

Absolutely. You can combine Hurma tools like listemployees with external databases or communication tools inside a single LangGraph pipeline to automate onboarding or offboarding.

Link Hurma HR tools directly to your LangChain chains to automate leave requests and candidate pipeline tracking without custom API glue.

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 LangChain

Create your Vinkius account to connect Hurma 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 Hurma with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-step recruitment pipelines in LangChain

The `list_candidates` tool lets your LangChain agent pull active applicants and feed them directly into evaluation chains. You can build a LangChain system where the agent fetches a candidate profile, checks their details with `get_candidate_details`, and assigns them to the correct step in your pipeline. LangSmith tracks every step of this Hurma chain so you see exactly how the agent evaluates each applicant. If a candidate looks promising, the LangChain chain automatically schedules their next step using `list_vacancy_stages` without manual handoffs using this MCP integration.

Automated time-off management chains

Your LangChain agent uses `get_vacation_balance` via the Hurma MCP Server to check an employee's remaining time off before initiating any leave requests. Instead of writing custom logic to parse remaining days in LangChain, the agent reads the balance directly and decides if the request fits company policies. If the balance is sufficient, the LangChain chain executes `create_leave_request` to finalize the entry. This keeps your HR team out of the loop for standard requests while maintaining complete traceability in your LangChain logs.

On-demand payroll and overtime reporting

The `export_overtimes` tool allows your LangChain agent to pull overtime hours and pass them to downstream billing or accounting chains. You can chain this Hurma data directly with external accounting APIs to calculate monthly payouts inside LangChain. By combining employee records from `get_employee_details` with active Hurma overtime exports, your LangChain system builds accurate reports. This setup eliminates the need to manually copy records between your Hurma database and other LangChain-connected tools.

Setup guide

Set up Hurma 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 Hurma 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({
    "hurma-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 Hurma 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 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 LangChain

You install the LangChain MCP adapter package and initialize the client using the Vinkius transport URL. Once connected, call `get_tools()` to pass all twelve Hurma tools directly to your agent's tool list.

Yes, you can construct a sequential chain or a ReAct agent that first calls `get_vacation_balance` to verify available days. If the balance is sufficient, the agent immediately calls `create_leave_request` to submit the form in the same execution run.

LangSmith logs every single API call made by the Hurma server, showing you the exact inputs and outputs. You can inspect the payload of `get_employee_details` or track why a candidate creation failed during a run.

Absolutely. You can combine Hurma tools like `list_employees` with external databases or communication tools inside a single LangGraph pipeline to automate onboarding or offboarding.

All employee profiles, vacation records, and candidate details retrieved via `get_employee_details` remain inside your execution environment. Vinkius runs the Hurma MCP server in a sandboxed isolate, meaning your sensitive HR data is never stored or used to train public models.

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