How to Use the TOTVS MCP in LangChain

Q: How can I use TOTVS and LangChain together for employee onboarding?

Your agent first calls listemployees to confirm the person exists in the system. After verifying, it uses getemployeedetails to pull all necessary HR data points needed for provisioning. This two-step process ensures you have a complete record before moving on.

Q: Can I track Fluig processes with TOTVS and LangChain?

Absolutely. You can use listprocesses to view all available BPM flows, then pinpoint a specific request using getprocessrequest. Finally, you use moveprocessrequest to advance that workflow's status. It lets your agent manage the entire process lifecycle.

Q: What does the TOTVS and LangChain integration know about document management?

The server provides listdocuments to check for files within the Fluig ECM system. Your agent can list available documents, giving you visibility into stored corporate records.

Build multi-step TOTVS automation chains with LangChain.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect TOTVS MCP to LangChain

Create your Vinkius account to connect TOTVS 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 TOTVS with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Manage Employee Data Flow

To get an employee's full record, your agent calls `get_employee_details`. This tool accepts a specific ID and returns comprehensive HR data. You can then follow up by using `list_employees` to verify the initial set of records against the detailed result. This means you build chains that check who exists first, and *then* grab their deep profile—all in one run. It’s perfect for complex onboarding workflows where multiple lookups are needed.

Process Finance Lookups

Check payable accounts using `list_payments` to get a list of pending vendors. You can then take specific invoice details from that list and query them further with `get_rm_data`. This combination lets you validate if the general ledger data matches the expected payments. It's useful for automating reconciliation reports where you need both high-level summaries and granular record checks. The whole process stays within a single, traceable chain.

Control BPM Workflows

Start by listing all available business processes using `list_processes` to see what's running in Fluig. Once you pinpoint the target workflow, use `get_process_request` to grab its current status and details. You can then advance it with `move_process_request`, moving the whole request state forward. This lets your agent not just read data, but actively drive a business process from beginning to end. The result of checking the process request feeds directly into advancing that step.

Setup guide

Set up TOTVS 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 TOTVS 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({
    "totvs-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 TOTVS 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 TOTVS. 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 TOTVS 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 TOTVS MCP in LangChain

Your agent first calls `list_employees` to confirm the person exists in the system. After verifying, it uses `get_employee_details` to pull all necessary HR data points needed for provisioning. This two-step process ensures you have a complete record before moving on.

You can automate multi-stage finance checks. For example, your agent lists all accounts payable using `list_payments`, then selects a specific vendor invoice ID to query the detailed record via `get_rm_data`. It handles the entire data validation pipeline.

Absolutely. You can use `list_processes` to view all available BPM flows, then pinpoint a specific request using `get_process_request`. Finally, you use `move_process_request` to advance that workflow's status. It lets your agent manage the entire process lifecycle.

The server touches several key areas, including HR employee records, Finance accounts payable/receivable, and BPM workflow request details. It's a broad set of operational data.

The server provides `list_documents` to check for files within the Fluig ECM system. Your agent can list available documents, giving you visibility into stored corporate 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