How to Use the TOTVS MCP in Pydantic AI

Q: Can I ensure TOTVS company data integrity with Pydantic AI?

Yes. When calling listcompanies, or any other tool, the resulting list is validated against a Pydantic model. You'll get clean Python objects, not messy JSON that could break your application.

Q: How does Pydantic AI manage data from TOTVS?

It validates the output of every tool call—whether it’s listemployees or getavailableservices. This means you get reliable, typed data regardless of how the underlying MCP Server executes the query.

Q: Does Pydantic AI support querying custom TOTVS records?

Yes. The getrmdata tool allows you to pull specific, customized records from any RM DataServer. Crucially, even this highly variable data is validated against your schema.

Pydantic AI: Build type-safe agents for TOTVS ERP and BPM tools.

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 Pydantic AI

Create your Vinkius account to connect TOTVS to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate Employee Data Types

When fetching staff details, you can use `get_employee_details` or pull a list using `list_employees`. Pydantic ensures that the data returned from TOTVS matches your expected Python schema—no unexpected fields. This model-agnostic approach is great because it guarantees correctness. If the API response changes unexpectedly, the agent fails loudly with a validation error instead of silently corrupting your run.

Guarantee Financial Data Integrity

For finance tasks, whether listing accounts payable (`list_payments`) or checking receipts (`list_receipts`), Pydantic validates the data types at runtime. You know exactly what you're getting back. This level of type safety is critical when your agent needs to combine multiple sources, like cross-referencing a payment record with a document list via `list_documents`.

Schema Enforcement for BPM

Workflow management requires precision. You can check requests using `get_process_request`, and the data returned will conform to your defined schema. This applies when listing processes with `list_processes` or moving them via `move_process_request`. The entire MCP Server exposes eleven tools, allowing you to define strict schemas for every single operation—from simple company listings (`list_companies`) to complex data queries (`get_rm_data`).

Setup guide

Set up TOTVS MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "totvs-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to TOTVS tools.",
)

result = await agent.run("List recent TOTVS transactions")
print(result.output)

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 Pydantic AI

You define the expected schema for workflow tools. When you call `move_process_request`, Pydantic validates that the required inputs (like the process ID) are present and correct before your agent proceeds.

The server touches employee details, financial records (accounts payable/receivable), and BPM processes. Because of runtime validation, you can rely on the specific structure of these core business objects.

Yes. When calling `list_companies`, or any other tool, the resulting list is validated against a Pydantic model. You'll get clean Python objects, not messy JSON that could break your application.

It validates the output of every tool call—whether it’s `list_employees` or `get_available_services`. This means you get reliable, typed data regardless of how the underlying MCP Server executes the query.

Yes. The `get_rm_data` tool allows you to pull specific, customized records from any RM DataServer. Crucially, even this highly variable data is validated against your schema.

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