Which TOTVS systems are compatible with this MCP?

This MCP is designed to work with standard REST APIs from Protheus, RM, and Fluig. Ensure your specific instance has the relevant API modules enabled.

How do I find my TOTVS Base URL?

The Base URL is the address of your ERP or Fluig web service (e.g., `https://erp.mycompany.com:8080/rest`). You can find this in your system's technical documentation or environment settings.

Can I automatically advance a Fluig process request?

Yes! Use the `advance_process` tool with the specific Process Instance ID. Your agent will trigger the workflow transition based on the logic defined in Fluig.

TOTVS MCP Server for Pydantic AI 11 tools — connect in under 2 minutes

Name: TOTVS
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 11 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect TOTVS through the Vinkius and every tool is automatically validated against Pydantic schemas — catch errors at build time, not in production.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP

async def main():
    # Your Vinkius token — get it at cloud.vinkius.com
    server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

    agent = Agent(
        model="openai:gpt-4o",
        mcp_servers=[server],
        system_prompt=(
            "You are an assistant with access to TOTVS "
            "(11 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in TOTVS?"
    )
    print(result.data)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About TOTVS MCP Server

Connect your AI agents to TOTVS, the largest technology company in Brazil and Latin America. This MCP provides 10 tools to manage organizational data across Protheus, RM, and Fluig ecosystems, enabling seamless orchestration of HR, Financial, and Business Process Management (BPM) workflows.

Pydantic AI validates every TOTVS tool response against typed schemas, catching data inconsistencies at build time. Connect 11 tools through the Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code — full type safety, structured output guarantees, and dependency injection for testable agents.

What you can do

HR Orchestration — List employees and retrieve detailed profiles across the organization
Financial Control — Monitor accounts payable/receivable and list real-time receipts and payments
BPM Workflows — Track and advance process requests in Fluig and manage the Electronic Content Management (ECM) system
Multi-System Access — Unified interaction with Protheus, RM, and Fluig through a single AI interface

The TOTVS MCP Server exposes 11 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect TOTVS to Pydantic AI via MCP

Follow these steps to integrate the TOTVS MCP Server with Pydantic AI.

Install Pydantic AI

Run pip install pydantic-ai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 11 tools from TOTVS with type-safe schemas

Why Use Pydantic AI with the TOTVS MCP Server

Pydantic AI provides unique advantages when paired with TOTVS through the Model Context Protocol.

Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application

Model-agnostic architecture — switch between OpenAI, Anthropic, or Gemini without changing your TOTVS integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your TOTVS connection logic from agent behavior for testable, maintainable code

TOTVS + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the TOTVS MCP Server delivers measurable value.

Type-safe data pipelines: query TOTVS with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple TOTVS tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query TOTVS and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock TOTVS responses and write comprehensive agent tests

TOTVS MCP Tools for Pydantic AI (11)

These 11 tools become available when you connect TOTVS to Pydantic AI via MCP:

get_available_services

List available RM DataServers

get_employee_details

Get detailed information for a specific employee

get_process_request

Get details for a specific Fluig process request

get_rm_data

Query a specific record from an RM DataServer

list_companies

List all companies and branches in the Protheus environment

list_documents

List documents in the Fluig ECM

list_employees

List employees from the HR module

list_payments

List accounts payable (Finance)

list_processes

List all BPM processes in Fluig

list_receipts

List accounts receivable (Finance)

move_process_request

Advance a Fluig process request to the next state

Example Prompts for TOTVS in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with TOTVS immediately.

"List all active employees in my TOTVS RM environment."

"Show the accounts payable summary for this month from Protheus."

"List all pending workflow requests in Fluig."

Troubleshooting TOTVS MCP Server with Pydantic AI

Common issues when connecting TOTVS to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

TOTVS + Pydantic AI FAQ

Common questions about integrating TOTVS MCP Server with Pydantic AI.

How does Pydantic AI discover MCP tools?

Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.

Does Pydantic AI validate MCP tool responses?

Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.

Can I switch LLM providers without changing MCP code?

Absolutely. Pydantic AI abstracts the model layer — your TOTVS MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.