How to Use the TOTVS MCP in AutoGen

Q: Can AutoGen automate the movement of Fluig processes with TOTVS?

Yes. You assign agents roles—one monitoring listprocesses and another proposing an action using moveprocessrequest. The negotiation phase determines if, and how, the process request should advance.

Q: Is the document metadata from TOTVS secure when using AutoGen?

Yes. By listing documents with listdocuments, you gather metadata about Fluig ECM files. The agents can then use this information to check if required supporting documentation is present before advancing a process.

Multi-agent TOTVS systems for decision-making with AutoGen.

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 AutoGen

Create your Vinkius account to connect TOTVS to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automated HR Vetting

You set up competing agents—one to list all employees using `list_employees`, and another to check specific details via `get_employee_details`. These agents debate the best way to validate a new hire's status, converging on a final decision. The process is consensus-driven. This means you don't just run reports; multiple specialized agents negotiate the data retrieval, ensuring all necessary checks are performed before finalizing an employee record.

Negotiating Financial Status

A 'Finance Agent' calls `list_payments` to gather vendor invoices. A separate 'Compliance Agent' then queries a specific receivable using `get_rm_data`. These two agents challenge each other's assumptions about payment timing and required approvals. The result is a highly reasoned conclusion on the financial status, rather than just an API list. It’s decision-making between competing data sources.

Driving BPM Consensus

One agent uses `list_processes` to map the entire business process landscape. A second agent then attempts a state change using `move_process_request`. They debate if the current request is ready for advancement, flagging potential bottlenecks or missing approvals. The system converges on whether the workflow should move forward and what specific action is required next—a true multi-agent deliberation.

Setup guide

Set up TOTVS MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes TOTVS tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="TOTVS_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent TOTVS data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="TOTVS_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent TOTVS data")
    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 AutoGen

You build a system where multiple agents collaborate. One agent might call `list_employees` to see the roster, while another uses `get_employee_details` to validate specific department rules. The agents debate who is correct before delivering a final status.

The system allows for consensus-driven finance checks. Agents might compare data from `list_payments` against specific receivable records (`get_rm_data`) to negotiate a final payment approval status.

Yes. You assign agents roles—one monitoring `list_processes` and another proposing an action using `move_process_request`. The negotiation phase determines if, and how, the process request should advance.

The agents manage HR employee records, Finance accounts payable/receivable, and BPM workflow request details. They treat these operational domains as subjects for debate.

Yes. By listing documents with `list_documents`, you gather metadata about Fluig ECM files. The agents can then use this information to check if required supporting documentation is present before advancing a process.

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