How to Use the Lucca (HR & Finance Suite) MCP in LangChain

Q: How do I pass Lucca (HR & Finance Suite) tools to a LangChain agent?

Install langchain-mcp-adapters and initialize the MultiServerMCPClient pointing to your Vinkius endpoint. Call client.gettools() to fetch Lucca tools like listusers and pass them directly to your agent constructor.

Q: How does LangSmith help debug Lucca (HR & Finance Suite) tool calls in LangChain?

LangSmith logs the exact inputs and outputs of tools like getleavebalances or listexpensereports during execution. You see exactly what payload the agent received and why it decided to call the next tool in the chain.

Q: Is context maintained between different tool calls in a chain?

While the adapter is stateless by default, you can use client.session() to preserve context across multiple steps. This is useful when your agent needs to reference a user ID from getuser across multiple financial queries.

Build multi-step reasoning chains in LangChain that query Lucca HR directory data and approve expense reports automatically.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Lucca (HR & Finance Suite) MCP to LangChain

Create your Vinkius account to connect Lucca (HR & Finance Suite) 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 Lucca (HR & Finance Suite) with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Lucca employee lookups with LangChain agents

Let your LangChain agent pull directory data using `get_user` to verify who is requesting an expense review. The agent takes that output and feeds it directly into `list_expense_reports` to match files against the correct team budget. By routing these Lucca outputs sequentially, your LangChain agent runs multi-step verification without hardcoded logic. LangSmith tracks the whole execution path, exposing latency and token usage for every single Lucca tool call.

Multi-step time tracking and leave balance auditing

Combine `get_leave_balances` and `list_leaves` in a single LangGraph state machine to audit payroll discrepancies. Your LangChain agent inspects historical absences in Lucca, checks remaining balances, and flags anomalies for manual review. This setup turns complex Lucca HR workflows into predictable, observable LangChain chains using the MCP adapter. You run these Lucca pipelines statelessly or maintain context across multiple turns using the LangChain client session adapter.

Cross-reference departments for dynamic expense routing

Use `list_departments` to map corporate structures in LangChain before running financial checks via `list_expense_claims`. This framework calculates department-specific spending trends by matching individual Lucca claims to organizational nodes. Connecting this MCP Server to your LangChain chains lets you query live Cleemy and Timmi data alongside vector databases or external payroll APIs. The LangChain agent dynamically decides which Lucca endpoint to call based on the natural language request.

Setup guide

Set up Lucca (HR & Finance Suite) 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 Lucca (HR & Finance Suite) 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({
    "lucca-hr-finance-suite-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 Lucca (HR & Finance Suite) 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 Lucca. 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 Lucca (HR & Finance Suite) 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 Lucca (HR & Finance Suite) MCP in LangChain

Install `langchain-mcp-adapters` and initialize the `MultiServerMCPClient` pointing to your Vinkius endpoint. Call `client.get_tools()` to fetch Lucca tools like `list_users` and pass them directly to your agent constructor.

Yes, you can mix these tools with any of LangChain's 500+ integrations in a single graph. For example, an agent can pull timesheets with `list_timesheets` and immediately write that data to an external SQL database.

LangSmith logs the exact inputs and outputs of tools like `get_leave_balances` or `list_expense_reports` during execution. You see exactly what payload the agent received and why it decided to call the next tool in the chain.

While the adapter is stateless by default, you can use `client.session()` to preserve context across multiple steps. This is useful when your agent needs to reference a user ID from `get_user` across multiple financial queries.

Your Lucca timesheet and expense data never logs on external servers because Vinkius runs in an ephemeral, zero-trust sandbox. Only authorized LangChain runs can execute the underlying API calls via your secure single-token gateway.

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