How do I setup my Base64 Certificate and API credentials?

Log into your Efí account, go to **API > Applications**. Create an app to get the Client ID and Secret. Then generate a Production Certificate (`.p12`). Instead of uploading the file to Vinkius, use terminal command `base64 -i your_cert.p12` to convert it into a plaintext string, and paste that robust text directly into the MCP configuration.

Can I automatically verify if a customer paid a Pix charge just by chatting with my AI?

Yes! Provide the agent the exact transaction id (`txid`) of the generated Pix. The agent will query the `efi_get_pix_payment` tool and immediately tell you if the status is active, answered, or expired.

Does the integration support transferring money out (Cash-out)?

Yes. Using the `efi_send_pix` action, you can initiate outbound immediate payments requesting the agent to process a value directly to a receiver Pix key.

Can I query a history of paid bank slips (Boletos) at the end of the day or month?

Certainly. The `efi_list_boletos` and `efi_get_statement` tool allows you to perform large queries parsing begin/end dates to return summaries directly in your terminal.

Efí Pay (Gerencianet) MCP Server for Google ADK 8 tools — connect in under 2 minutes

Name: Efí Pay (Gerencianet)
Availability: InStock
Author: Vinkius

google.github.io/adk-docs/tools/mcp-tools

Built by Vinkius GDPR 8 Tools SDK

Google Agent Development Kit (ADK) is Google's framework for building production AI agents. Add Efí Pay (Gerencianet) as an MCP tool provider through Vinkius and your ADK agents can call every tool with full schema introspection.

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

from google.adk.agents import Agent
from google.adk.tools.mcp_tool import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import (
    StreamableHTTPConnectionParams,
)

# Your Vinkius token. get it at cloud.vinkius.com
mcp_tools = McpToolset(
    connection_params=StreamableHTTPConnectionParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    )
)

agent = Agent(
    model="gemini-2.5-pro",
    name="efi_pay_gerencianet_agent",
    instruction=(
        "You help users interact with Efí Pay (Gerencianet) "
        "using 8 available tools."
    ),
    tools=[mcp_tools],
)

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 Efí Pay (Gerencianet) MCP Server

The Efí Pay MCP Server connects your AI agent directly to one of Brazil's largest payment and digital account platforms (formerly Gerencianet). Command your agent to handle invoicing seamlessly using natural language.

Google ADK natively supports Efí Pay (Gerencianet) as an MCP tool provider. declare Vinkius Edge URL and the framework handles discovery, validation, and execution automatically. Combine 8 tools with Gemini's long-context reasoning for complex multi-tool workflows, with production-ready session management and evaluation built in.

What you can do

Pix Management — Generate dynamic immediate charges (Pix Cob), check specific payment statuses in real-time, and send Pix directly to external keys.
Traditional Invoicing — Emit traditional Brazilian bank slips (Boletos) with specified expiration dates, item totals, and payer documents (CPF/CNPJ).
Account Overviews — Ask your agent to retrieve your current Efí account balance or pull a complete historical banking statement over a defined date range.

The Efí Pay (Gerencianet) MCP Server exposes 8 tools through the Vinkius. Connect it to Google ADK 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 Efí Pay (Gerencianet) to Google ADK via MCP

Follow these steps to integrate the Efí Pay (Gerencianet) MCP Server with Google ADK.

Install Google ADK

Run pip install google-adk

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Create the agent

Save the code above and integrate into your ADK workflow

Explore tools

The agent will discover 8 tools from Efí Pay (Gerencianet) via MCP

Why Use Google ADK with the Efí Pay (Gerencianet) MCP Server

Google ADK provides unique advantages when paired with Efí Pay (Gerencianet) through the Model Context Protocol.

Google ADK natively supports MCP tool servers. declare a tool provider and the framework handles discovery, validation, and execution

Built on Gemini models, ADK provides long-context reasoning ideal for complex multi-tool workflows with Efí Pay (Gerencianet)

Production-ready features like session management, evaluation, and deployment come built-in. not bolted on

Seamless integration with Google Cloud services means you can combine Efí Pay (Gerencianet) tools with BigQuery, Vertex AI, and Cloud Functions

Efí Pay (Gerencianet) + Google ADK Use Cases

Practical scenarios where Google ADK combined with the Efí Pay (Gerencianet) MCP Server delivers measurable value.

Enterprise data agents: ADK agents query Efí Pay (Gerencianet) and cross-reference results with internal databases for comprehensive analysis

Multi-modal workflows: combine Efí Pay (Gerencianet) tool responses with Gemini's vision and language capabilities in a single agent

Automated compliance checks: schedule ADK agents to query Efí Pay (Gerencianet) regularly and flag policy violations or configuration drift

Internal tool platforms: build self-service agent platforms where teams connect their own MCP servers including Efí Pay (Gerencianet)

Efí Pay (Gerencianet) MCP Tools for Google ADK (8)

These 8 tools become available when you connect Efí Pay (Gerencianet) to Google ADK via MCP:

efi_create_boleto

Gerar um banco slip tradicional brasileiro (Boleto)

efi_create_pix_charge

Emitir cobrança imediata via Pix (Cob)

efi_get_balance

Consultar o resuldado / Saldo atual da conta digital (Efí Pay)

efi_get_pix_payment

Consultar um único pagamento Pix recebido específico

efi_get_statement

Consultar o Resumo (Statement / Extrato) das movimentações da conta

efi_list_boletos

Listar todos os Boletos e transações emitidos em um range de datas

efi_list_pix_charges

Consultar cobranças Pix (Cob) recebidas ou geradas num intervalo

efi_send_pix

Enviar um Pix em tempo real para terceiros

Example Prompts for Efí Pay (Gerencianet) in Google ADK

Ready-to-use prompts you can give your Google ADK agent to start working with Efí Pay (Gerencianet) immediately.

"Generate a dynamic Pix charge of R$ 150.00 expiring in 3600 seconds, and link it to my external key myemail@store.com."

"Check the status of the Pix payment holding the txid 'abc123zxy456'."

"Pull a list of my generated Boletos since September 1st, showing me only the unpaid ones."

Troubleshooting Efí Pay (Gerencianet) MCP Server with Google ADK

Common issues when connecting Efí Pay (Gerencianet) to Google ADK through the Vinkius, and how to resolve them.

McpToolset not found

Update: pip install --upgrade google-adk

Efí Pay (Gerencianet) + Google ADK FAQ

Common questions about integrating Efí Pay (Gerencianet) MCP Server with Google ADK.

How does Google ADK connect to MCP servers?

Import the MCP toolset class and pass the server URL. ADK discovers and registers all tools automatically, making them available to your agent's tool-use loop.

Can ADK agents use multiple MCP servers?

Yes. Declare multiple MCP tool providers in your agent configuration. ADK merges all tool schemas and the agent can call tools from any server in a single turn.

Which Gemini models work best with MCP tools?

Gemini 2.0 Flash and Pro models both support function calling required for MCP tools. Flash is recommended for latency-sensitive use cases, Pro for complex reasoning.