How to Use the TOTVS MCP in CrewAI

Q: What types of data can CrewAI access regarding TOTVS?

The crew accesses HR records (listemployees), financial ledgers (AP/AR), Protheus company structures, and Fluig ECM documents. The tools are diverse.

Q: What tools are available for TOTVS integration with CrewAI?

You can use tools like getrmdata, listdocuments, and various listing functions (listcompanies) to gather source data points for your specialized agents.

Run complex TOTVS operations using specialized collaborating agents with CrewAI.

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 CrewAI

Create your Vinkius account to connect TOTVS to CrewAI 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 CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Autonomous Reconciliation with CrewAI

You can assign a 'Reconciliation Agent' to compare financial records. This agent uses `list_payments` and `list_receipts` simultaneously, comparing the two datasets for discrepancies. Another agent can monitor this comparison process. If a mismatch is found, the system escalates the issue by flagging specific record IDs that require human review.

Comprehensive Directory Creation with CrewAI

Need an organizational report? You deploy specialized agents: one runs `list_employees` to get names, and a second agent uses `get_employee_details` for department specifics. A third agent then cross-references this data against all known branches using `list_companies`. The output is a cohesive document that synthesizes multiple sources of employee directory information.

BPM Oversight and Document Auditing with CrewAI

Set up a process audit crew. One agent uses `list_processes` to gather all active workflows. A second specialized agent then checks the associated documentation by calling `list_documents`. This connects the workflow state to the source records. The whole operation runs autonomously, summarizing which processes lack necessary supporting documents.

Setup guide

Set up TOTVS MCP in CrewAI

Prerequisites

Python 3.10+ installed
crewai package (pip install crewai)
Active Vinkius subscription with a valid endpoint token

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke TOTVS tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="TOTVS Analyst",
    goal="Access and analyze TOTVS data via MCP.",
    backstory="Expert analyst with direct TOTVS access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent TOTVS transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

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

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="TOTVS Analyst",
        goal="Access and analyze TOTVS data via MCP.",
        backstory="Expert analyst with direct TOTVS access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent TOTVS transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

It doesn't run a single agent; it assigns roles. One agent researches using tools like `list_processes`, another analyzes the results, and a third takes action via a tool like `move_process_request`.

The crew accesses HR records (`list_employees`), financial ledgers (AP/AR), Protheus company structures, and Fluig ECM documents. The tools are diverse.

Yes. You can build autonomous operations like discrepancy detection between accounts payable records using `list_payments` and the system's built-in monitoring agent handles escalation if discrepancies occur.

The server touches employee details (names, job roles) and financial records. The moderator agent ensures that sensitive information is only passed to authorized downstream consumers.

You can use tools like `get_rm_data`, `list_documents`, and various listing functions (`list_companies`) to gather source data points for your specialized agents.

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