How to Use the Mercado Pago MCP in Google ADK

Q: Can Google ADK filter which Mercado Pago tools are exposed to Gemini?

Yes, you can use the optional toolnames filter in the ADK toolset configuration. This lets you restrict the agent to read-only tools like listpaymentmethods if you want to prevent unauthorized refunds.

Q: How does Google ADK handle CPF validation before calling Mercado Pago tools?

The agent executes getidentificationtypes to fetch valid Brazilian document structures. It parses the user's input, confirms it matches CNPJ or CPF rules, and then invokes the customer creation tool.

Q: Can I use Google ADK to refund transactions automatically?

Yes, the agent uses refundpayment to reverse charges when processing customer support tickets. You can set rules in your agent code to limit refunds to specific transaction IDs found via searchpayments.

Connect Gemini agents to Mercado Pago with Google ADK using our secure MCP Server to automate enterprise reconciliation.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Mercado Pago MCP to Google ADK

Create your Vinkius account to connect Mercado Pago to Google ADK 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 Mercado Pago with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Reconcile Brazil Sales with Google ADK

The `search_payments` tool fetches historical transaction data, which your Gemini agent processes inside its massive 1M-token context window. Using Google ADK, the agent correlates these live payment records with your enterprise data warehouse tables. The agent identifies discrepancies between bank statements and system records without losing track of older transactions. It then calls `get_payment` to inspect specific anomalies and update your ledger in real time.

Generate Checkout Preferences via Google ADK

The `create_preference` tool structures hosted checkout sessions based on user profiles analyzed by your Vertex AI models through our MCP integration. Google ADK lets your agent read customer behavior patterns and immediately build tailored checkout configurations. Once the preference is built, the agent retrieves the checkout link using `get_preference`. The agent displays the link directly to the user, keeping the conversation fluid while steering them toward high-converting payment methods.

Issue Pix Payments with Google ADK

The `create_pix_payment` tool generates instant QR codes for immediate settlement in Brazil. Google ADK connects this tool directly to your Gemini-powered chat interfaces, letting users request and receive payment codes in a single turn. The agent pulls current pricing data from your internal systems, formats the request, and displays the QR payload. Customers scan the code, and your agent monitors the settlement status using continuous polling loops.

Setup guide

Set up Mercado Pago MCP in Google ADK

Prerequisites

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

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Mercado Pago tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Mercado Pago_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Mercado Pago tools via MCP.",
    tools=mcp_tools,
)

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 Mercado Pago. 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 Mercado Pago 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 Mercado Pago MCP in Google ADK

Install google-adk and define a McpToolset pointing to your Vinkius HTTP endpoint. Pass this toolset into your LlmAgent configuration to give Gemini access to all 12 MCP tools.

Yes, you can use the optional tool_names filter in the ADK toolset configuration. This lets you restrict the agent to read-only tools like list_payment_methods if you want to prevent unauthorized refunds.

The agent executes get_identification_types to fetch valid Brazilian document structures. It parses the user's input, confirms it matches CNPJ or CPF rules, and then invokes the customer creation tool.

Yes, the agent uses refund_payment to reverse charges when processing customer support tickets. You can set rules in your agent code to limit refunds to specific transaction IDs found via search_payments.

Your credential is encrypted and injected directly into the ephemeral MCP V8 sandbox runtime. Vinkius processes all transactions without persisting sensitive payloads like customer names or card tokens.

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