How to Use the Conta Azul MCP in LlamaIndex

Q: How do I index Conta Azul sales logs in LlamaIndex?

Call listsales using the McpToolSpec to extract your historical transactions. You then pass these documents to your vector indexer to make them searchable.

Q: Can LlamaIndex query Conta Azul customer profiles directly?

Yes, the FunctionAgent uses getcustomer to fetch specific profiles during live query sessions. This keeps your RAG system updated with the latest fiscal details.

Q: What is the setup for connecting LlamaIndex to Conta Azul?

Run pip install llama-index-tools-mcp and initialize the MCP client. You then convert the server tools using McpToolSpec and register them with your agent.

Q: Does this setup support filtering by specific ERP categories?

The agent uses listcategories to pull your DRE structure and filter financial records accordingly. This allows you to restrict semantic searches to specific expense or revenue brackets.

Index Conta Azul ERP transactions into LlamaIndex vector stores to query live Brazilian financial data without hallucinations.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Conta Azul MCP to LlamaIndex

Create your Vinkius account to connect Conta Azul 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 Conta Azul with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Semantically index Conta Azul with LlamaIndex

The `list_sales` tool pulls your complete transaction history from the ERP to populate your local vector database. LlamaIndex indexes these raw sales logs, allowing your agent to run semantic searches over past invoices. Instead of guessing numbers, the model retrieves actual records grounded in your real-world financial data. You query this index using natural language to find specific payment trends. The framework matches your questions against the indexed `get_sale` outputs to deliver verified figures.

Grounded contract search using MCP Server tools

The `list_contracts` tool extracts active recurring agreements and their expiration dates directly from the ERP. Your LlamaIndex RAG pipeline ingest these contracts to build a searchable knowledge base of customer obligations. This eliminates hallucinations because the system checks the vector store before answering questions about renewals. When a client asks about their next bill, the agent queries this specific index. It formats the response using real data pulled through this MCP Server.

Live product and service inventory lookups

The `get_product` tool retrieves individual physical inventory specs, including unit measurements and SKU values. LlamaIndex combines this live data with your unstructured product catalogs to resolve complex inventory queries. The agent checks current ERP records before confirming whether an item is available for a new sale. For service-based operations, the `list_services` tool provides the exact pricing structures registered in your accounting. This ensures your sales agents always quote the correct rates during client interactions.

Setup guide

Set up Conta Azul 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 Conta Azul 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 Conta Azul tools.",
)
response = await agent.run("List recent Conta Azul 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 Conta Azul. 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 Conta Azul 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 Conta Azul MCP in LlamaIndex

Call `list_sales` using the `McpToolSpec` to extract your historical transactions. You then pass these documents to your vector indexer to make them searchable.

Yes, the `FunctionAgent` uses `get_customer` to fetch specific profiles during live query sessions. This keeps your RAG system updated with the latest fiscal details.

Run `pip install llama-index-tools-mcp` and initialize the MCP client. You then convert the server tools using `McpToolSpec` and register them with your agent.

The agent uses `list_categories` to pull your DRE structure and filter financial records accordingly. This allows you to restrict semantic searches to specific expense or revenue brackets.

Your DRE categories, customer tax IDs, and bank balances are processed via the MCP Server in secure, isolated memory spaces. Vinkius handles the API tokens safely, ensuring your financial credentials are never exposed to the LLM provider.

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