How to Use the TOTVS MCP in LlamaIndex

Q: How can I use TOTVS and LlamaIndex together to investigate employee records?

You index employee lists using listemployees. Then, you build a searchable knowledge base around that HR data. You can ask natural language questions—like 'Show me employees in department X'—and the system provides answers grounded in the TOTVS source.

Q: What kind of financial reports can I generate with TOTVS and LlamaIndex?

By indexing results from listpayments and listreceipts, you create a unified, queryable index for your finance department. You don't just get raw lists; you get semantic answers about the status or type of financial record.

Q: Can I track Fluig process history using TOTVS and LlamaIndex?

Yes. After running getprocessrequest, that detailed output gets indexed into your RAG application. This means you can query the historical context of a specific request, answering questions about its status or movement.

Q: Does the TOTVS and LlamaIndex connection help with document management data privacy?

Yes. By indexing documents pulled using listdocuments, you build a searchable catalog of corporate records, helping manage access to stored file metadata.

Index TOTVS operational data and search it with LlamaIndex.

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 LlamaIndex

Create your Vinkius account to connect TOTVS 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 TOTVS with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Querying HR Records

When you run `list_employees`, the result populates your knowledge base, making every employee entry searchable. You can then query this data to find specific details without needing a complex tool call like `get_employee_details`. The full record becomes part of the index for semantic search. This means instead of just running a lookup, you ask a question—like 'Who was hired last month?'—and LlamaIndex grounds the answer in the actual HR data retrieved by the MCP Server.

Financial Record Search

LlamaIndex indexes results from both accounts payable and receivable. By querying `list_payments` or `list_receipts`, you aren't just getting a list; you're adding structured, queryable financial records to your knowledge base. You can ask questions spanning multiple transactions. This capability lets developers build RAG applications that answer complex finance queries using the actual data pulled from the TOTVS system.

Tracking BPM History

You use `list_processes` to index all available business workflows. If you query a specific process request, `get_process_request`, that output is also stored in your vector store. This allows you to retrieve historical context for processes. Instead of just seeing the current status, LlamaIndex lets you ask, 'What was the typical flow for this type of request?' and it pulls answers based on past data.

Setup guide

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

You index employee lists using `list_employees`. Then, you build a searchable knowledge base around that HR data. You can ask natural language questions—like 'Show me employees in department X'—and the system provides answers grounded in the TOTVS source.

By indexing results from `list_payments` and `list_receipts`, you create a unified, queryable index for your finance department. You don't just get raw lists; you get semantic answers about the status or type of financial record.

Yes. After running `get_process_request`, that detailed output gets indexed into your RAG application. This means you can query the historical context of a specific request, answering questions about its status or movement.

The server touches HR employee records, Finance accounts payable/receivable, and BPM workflow request details. These live API results form the searchable knowledge base.

Yes. By indexing documents pulled using `list_documents`, you build a searchable catalog of corporate records, helping manage access to stored file metadata.

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