How to Use the intelliHR MCP in LangChain

Run LangChain agents that pull live organizational charts and employee profiles directly into your processing chains.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect intelliHR MCP to LangChain

Create your Vinkius account to connect intelliHR 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 intelliHR with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain HR Lookups with LangChain

Your agent uses `list_people` to find matching team members and then immediately passes those IDs to `get_person` to extract specific profile details. This setup lets you build multi-step reasoning pipelines where each tool call feeds the next one. By feeding these outputs directly into your LangChain prompt templates, you bypass manual script writing entirely. LangSmith traces every step, showing you the exact inputs and outputs of each MCP tool call in real-time.

Audit Pay Tiers in Multi-Step Workflows

The `list_remuneration` tool exposes salary structures, which your agent can cross-reference against job definitions retrieved via `list_jobs`. You can run these checks across multiple servers, aggregating compensation data with external financial APIs in a single run. Since the client is stateless by default, you can spin up clean, isolated runs for every audit. If you need to keep track of a complex, multi-step investigation, just initiate a session to maintain context across several tool execution steps.

Map Team Locations and Skills Dynamically

Your agent calls `list_locations` to map where your staff is based, while simultaneously running `list_skills` to see what expertise exists in those offices. Combining these data points allows your agent to suggest project teams based on physical proximity and actual technical capabilities. Integrating this MCP Server into your existing chains takes only a few lines of Python. You get raw, structured data directly from your HR platform, allowing your models to make decisions based on real organizational facts rather than guesses.

Setup guide

Set up intelliHR 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 intelliHR 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({
    "intellihr-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 intelliHR 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 intelliHR. 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 intelliHR 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 intelliHR MCP in LangChain

You install the adapter package and initialize the client with your endpoint. Call the tool retrieval method on your client instance and pass that list straight to your agent constructor. The agent then decides when to call tools like `list_people` based on user prompts.

Yes, you can track this easily. When you run your agent with LangSmith enabled, every call to `list_positions` or `list_training` is recorded with precise timestamps. You will see exactly how long the server takes to return organizational data.

Your chains should include error-handling wrappers to catch rate limits during heavy lookups. If an agent calls `list_users` too frequently, the server returns standard rate limit headers. You can configure your run loops to pause and retry automatically.

Absolutely. You can register this server alongside your SQL database tools in a single LangChain agent. The agent can pull employee names from the HR platform and instantly write them to your local database.

All requests run inside an isolated V8 sandbox, preventing any local data caching or leakage. Your employee remuneration and training records are encrypted in transit and never stored on our servers. The connection uses ephemeral tokens that expire immediately after your agent finishes its run.

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