How to Use the Mercado Pago MCP in LlamaIndex

Q: How do I connect the Mercado Pago MCP Server to LlamaIndex?

Install the required adapter with pip install llama-index-tools-mcp and initialize the BasicMCPClient. Convert the tools using McpToolSpec to make them available to your FunctionAgent.

Q: Can LlamaIndex index Pix QR codes generated by Mercado Pago?

Yes, when you call createpixpayment, the resulting QR code data and payment ID are returned. LlamaIndex can index this payload so your agent can retrieve active QR codes for customers.

Q: How does LlamaIndex handle Mercado Pago identification types?

Your agent calls getidentificationtypes to fetch valid document formats like CPF or CNPJ. It indexes these formats to validate user inputs before creating a new customer profile.

Q: Can I limit which Mercado Pago tools LlamaIndex can access on this MCP Server?

Yes, you can use the allowedtools filter in your client setup to restrict access. This ensures your agent only calls specific tools like listpaymentmethods while blocking refund capabilities.

Index live Mercado Pago transaction data into your LlamaIndex vector stores for query grounding.

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 LlamaIndex

Create your Vinkius account to connect Mercado Pago to LlamaIndex 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 LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index payment records into LlamaIndex

The `search_payments` tool retrieves transaction histories so your LlamaIndex pipeline can convert raw API responses into searchable vector embeddings. This prevents your agent from guessing transaction details by grounding answers in actual payment records. You can query past transactions using semantic search. The pipeline matches user queries with specific payment metadata retrieved from the server.

Query checkout configurations dynamically

The `get_preference` tool retrieves active checkout configurations from your Mercado Pago account. Your LlamaIndex agent uses this data to verify active payment links and ensure checkout URLs match current inventory. By loading these configurations into an index, you can ask your agent which preferences are active. This eliminates the need to manually browse the developer dashboard.

Context-aware customer profile lookup

The `get_customer` tool pulls buyer profiles and saved cards directly into your query engine. This MCP Server lets your agent cross-reference customer profiles with support tickets indexed in your vector database. This architecture ensures your agent has the exact context of who is buying before suggesting payment methods. It connects transaction data with user history in a single query.

Setup guide

Set up Mercado Pago MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Mercado Pago MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Mercado Pago tools.",
)
response = await agent.run("List recent Mercado Pago data")

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 LlamaIndex

Install the required adapter with `pip install llama-index-tools-mcp` and initialize the BasicMCPClient. Convert the tools using McpToolSpec to make them available to your FunctionAgent.

Yes, when you call `create_pix_payment`, the resulting QR code data and payment ID are returned. LlamaIndex can index this payload so your agent can retrieve active QR codes for customers.

Your agent calls `get_identification_types` to fetch valid document formats like CPF or CNPJ. It indexes these formats to validate user inputs before creating a new customer profile.

Yes, you can use the allowed_tools filter in your client setup to restrict access. This ensures your agent only calls specific tools like `list_payment_methods` while blocking refund capabilities.

Sensitive customer records and identification numbers are never cached in the index. The MCP Server acts as an ephemeral bridge, passing data directly to your client without persistent storage.

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